summaryrefslogtreecommitdiffstats
path: root/arch/i386/kernel/apic.c
blob: ce75e71b694fc1d970c080ffdef2d6234f0fd05d (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
/*
 *	Local APIC handling, local APIC timers
 *
 *	(c) 1999, 2000 Ingo Molnar <mingo@redhat.com>
 *
 *	Fixes
 *	Maciej W. Rozycki	:	Bits for genuine 82489DX APICs;
 *					thanks to Eric Gilmore
 *					and Rolf G. Tews
 *					for testing these extensively.
 *	Maciej W. Rozycki	:	Various updates and fixes.
 *	Mikael Pettersson	:	Power Management for UP-APIC.
 *	Pavel Machek and
 *	Mikael Pettersson	:	PM converted to driver model.
 */

#include <linux/init.h>

#include <linux/mm.h>
#include <linux/delay.h>
#include <linux/bootmem.h>
#include <linux/smp_lock.h>
#include <linux/interrupt.h>
#include <linux/mc146818rtc.h>
#include <linux/kernel_stat.h>
#include <linux/sysdev.h>
#include <linux/cpu.h>
#include <linux/module.h>

#include <asm/atomic.h>
#include <asm/smp.h>
#include <asm/mtrr.h>
#include <asm/mpspec.h>
#include <asm/desc.h>
#include <asm/arch_hooks.h>
#include <asm/hpet.h>
#include <asm/i8253.h>
#include <asm/nmi.h>

#include <mach_apic.h>
#include <mach_apicdef.h>
#include <mach_ipi.h>

#include "io_ports.h"

/*
 * cpu_mask that denotes the CPUs that needs timer interrupt coming in as
 * IPIs in place of local APIC timers
 */
static cpumask_t timer_bcast_ipi;

/*
 * Knob to control our willingness to enable the local APIC.
 */
int enable_local_apic __initdata = 0; /* -1=force-disable, +1=force-enable */

/*
 * Debug level
 */
int apic_verbosity;


static void apic_pm_activate(void);

static int modern_apic(void)
{
	unsigned int lvr, version;
	/* AMD systems use old APIC versions, so check the CPU */
	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
		boot_cpu_data.x86 >= 0xf)
		return 1;
	lvr = apic_read(APIC_LVR);
	version = GET_APIC_VERSION(lvr);
	return version >= 0x14;
}

/*
 * 'what should we do if we get a hw irq event on an illegal vector'.
 * each architecture has to answer this themselves.
 */
void ack_bad_irq(unsigned int irq)
{
	printk("unexpected IRQ trap at vector %02x\n", irq);
	/*
	 * Currently unexpected vectors happen only on SMP and APIC.
	 * We _must_ ack these because every local APIC has only N
	 * irq slots per priority level, and a 'hanging, unacked' IRQ
	 * holds up an irq slot - in excessive cases (when multiple
	 * unexpected vectors occur) that might lock up the APIC
	 * completely.
	 * But only ack when the APIC is enabled -AK
	 */
	if (cpu_has_apic)
		ack_APIC_irq();
}

void __init apic_intr_init(void)
{
#ifdef CONFIG_SMP
	smp_intr_init();
#endif
	/* self generated IPI for local APIC timer */
	set_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);

	/* IPI vectors for APIC spurious and error interrupts */
	set_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
	set_intr_gate(ERROR_APIC_VECTOR, error_interrupt);

	/* thermal monitor LVT interrupt */
#ifdef CONFIG_X86_MCE_P4THERMAL
	set_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
#endif
}

/* Using APIC to generate smp_local_timer_interrupt? */
int using_apic_timer __read_mostly = 0;

static int enabled_via_apicbase;

void enable_NMI_through_LVT0 (void * dummy)
{
	unsigned int v, ver;

	ver = apic_read(APIC_LVR);
	ver = GET_APIC_VERSION(ver);
	v = APIC_DM_NMI;			/* unmask and set to NMI */
	if (!APIC_INTEGRATED(ver))		/* 82489DX */
		v |= APIC_LVT_LEVEL_TRIGGER;
	apic_write_around(APIC_LVT0, v);
}

int get_physical_broadcast(void)
{
	if (modern_apic())
		return 0xff;
	else
		return 0xf;
}

int get_maxlvt(void)
{
	unsigned int v, ver, maxlvt;

	v = apic_read(APIC_LVR);
	ver = GET_APIC_VERSION(v);
	/* 82489DXs do not report # of LVT entries. */
	maxlvt = APIC_INTEGRATED(ver) ? GET_APIC_MAXLVT(v) : 2;
	return maxlvt;
}

void clear_local_APIC(void)
{
	int maxlvt;
	unsigned long v;

	maxlvt = get_maxlvt();

	/*
	 * Masking an LVT entry can trigger a local APIC error
	 * if the vector is zero. Mask LVTERR first to prevent this.
	 */
	if (maxlvt >= 3) {
		v = ERROR_APIC_VECTOR; /* any non-zero vector will do */
		apic_write_around(APIC_LVTERR, v | APIC_LVT_MASKED);
	}
	/*
	 * Careful: we have to set masks only first to deassert
	 * any level-triggered sources.
	 */
	v = apic_read(APIC_LVTT);
	apic_write_around(APIC_LVTT, v | APIC_LVT_MASKED);
	v = apic_read(APIC_LVT0);
	apic_write_around(APIC_LVT0, v | APIC_LVT_MASKED);
	v = apic_read(APIC_LVT1);
	apic_write_around(APIC_LVT1, v | APIC_LVT_MASKED);
	if (maxlvt >= 4) {
		v = apic_read(APIC_LVTPC);
		apic_write_around(APIC_LVTPC, v | APIC_LVT_MASKED);
	}

/* lets not touch this if we didn't frob it */
#ifdef CONFIG_X86_MCE_P4THERMAL
	if (maxlvt >= 5) {
		v = apic_read(APIC_LVTTHMR);
		apic_write_around(APIC_LVTTHMR, v | APIC_LVT_MASKED);
	}
#endif
	/*
	 * Clean APIC state for other OSs:
	 */
	apic_write_around(APIC_LVTT, APIC_LVT_MASKED);
	apic_write_around(APIC_LVT0, APIC_LVT_MASKED);
	apic_write_around(APIC_LVT1, APIC_LVT_MASKED);
	if (maxlvt >= 3)
		apic_write_around(APIC_LVTERR, APIC_LVT_MASKED);
	if (maxlvt >= 4)
		apic_write_around(APIC_LVTPC, APIC_LVT_MASKED);

#ifdef CONFIG_X86_MCE_P4THERMAL
	if (maxlvt >= 5)
		apic_write_around(APIC_LVTTHMR, APIC_LVT_MASKED);
#endif
	v = GET_APIC_VERSION(apic_read(APIC_LVR));
	if (APIC_INTEGRATED(v)) {	/* !82489DX */
		if (maxlvt > 3)		/* Due to Pentium errata 3AP and 11AP. */
			apic_write(APIC_ESR, 0);
		apic_read(APIC_ESR);
	}
}

void __init connect_bsp_APIC(void)
{
	if (pic_mode) {
		/*
		 * Do not trust the local APIC being empty at bootup.
		 */
		clear_local_APIC();
		/*
		 * PIC mode, enable APIC mode in the IMCR, i.e.
		 * connect BSP's local APIC to INT and NMI lines.
		 */
		apic_printk(APIC_VERBOSE, "leaving PIC mode, "
				"enabling APIC mode.\n");
		outb(0x70, 0x22);
		outb(0x01, 0x23);
	}
	enable_apic_mode();
}

void disconnect_bsp_APIC(int virt_wire_setup)
{
	if (pic_mode) {
		/*
		 * Put the board back into PIC mode (has an effect
		 * only on certain older boards).  Note that APIC
		 * interrupts, including IPIs, won't work beyond
		 * this point!  The only exception are INIT IPIs.
		 */
		apic_printk(APIC_VERBOSE, "disabling APIC mode, "
				"entering PIC mode.\n");
		outb(0x70, 0x22);
		outb(0x00, 0x23);
	}
	else {
		/* Go back to Virtual Wire compatibility mode */
		unsigned long value;

		/* For the spurious interrupt use vector F, and enable it */
		value = apic_read(APIC_SPIV);
		value &= ~APIC_VECTOR_MASK;
		value |= APIC_SPIV_APIC_ENABLED;
		value |= 0xf;
		apic_write_around(APIC_SPIV, value);

		if (!virt_wire_setup) {
			/* For LVT0 make it edge triggered, active high, external and enabled */
			value = apic_read(APIC_LVT0);
			value &= ~(APIC_MODE_MASK | APIC_SEND_PENDING |
				APIC_INPUT_POLARITY | APIC_LVT_REMOTE_IRR |
				APIC_LVT_LEVEL_TRIGGER | APIC_LVT_MASKED );
			value |= APIC_LVT_REMOTE_IRR | APIC_SEND_PENDING;
			value = SET_APIC_DELIVERY_MODE(value, APIC_MODE_EXTINT);
			apic_write_around(APIC_LVT0, value);
		}
		else {
			/* Disable LVT0 */
			apic_write_around(APIC_LVT0, APIC_LVT_MASKED);
		}

		/* For LVT1 make it edge triggered, active high, nmi and enabled */
		value = apic_read(APIC_LVT1);
		value &= ~(
			APIC_MODE_MASK | APIC_SEND_PENDING |
			APIC_INPUT_POLARITY | APIC_LVT_REMOTE_IRR |
			APIC_LVT_LEVEL_TRIGGER | APIC_LVT_MASKED);
		value |= APIC_LVT_REMOTE_IRR | APIC_SEND_PENDING;
		value = SET_APIC_DELIVERY_MODE(value, APIC_MODE_NMI);
		apic_write_around(APIC_LVT1, value);
	}
}

void disable_local_APIC(void)
{
	unsigned long value;

	clear_local_APIC();

	/*
	 * Disable APIC (implies clearing of registers
	 * for 82489DX!).
	 */
	value = apic_read(APIC_SPIV);
	value &= ~APIC_SPIV_APIC_ENABLED;
	apic_write_around(APIC_SPIV, value);

	if (enabled_via_apicbase) {
		unsigned int l, h;
		rdmsr(MSR_IA32_APICBASE, l, h);
		l &= ~MSR_IA32_APICBASE_ENABLE;
		wrmsr(MSR_IA32_APICBASE, l, h);
	}
}

/*
 * This is to verify that we're looking at a real local APIC.
 * Check these against your board if the CPUs aren't getting
 * started for no apparent reason.
 */
int __init verify_local_APIC(void)
{
	unsigned int reg0, reg1;

	/*
	 * The version register is read-only in a real APIC.
	 */
	reg0 = apic_read(APIC_LVR);
	apic_printk(APIC_DEBUG, "Getting VERSION: %x\n", reg0);
	apic_write(APIC_LVR, reg0 ^ APIC_LVR_MASK);
	reg1 = apic_read(APIC_LVR);
	apic_printk(APIC_DEBUG, "Getting VERSION: %x\n", reg1);

	/*
	 * The two version reads above should print the same
	 * numbers.  If the second one is different, then we
	 * poke at a non-APIC.
	 */
	if (reg1 != reg0)
		return 0;

	/*
	 * Check if the version looks reasonably.
	 */
	reg1 = GET_APIC_VERSION(reg0);
	if (reg1 == 0x00 || reg1 == 0xff)
		return 0;
	reg1 = get_maxlvt();
	if (reg1 < 0x02 || reg1 == 0xff)
		return 0;

	/*
	 * The ID register is read/write in a real APIC.
	 */
	reg0 = apic_read(APIC_ID);
	apic_printk(APIC_DEBUG, "Getting ID: %x\n", reg0);

	/*
	 * The next two are just to see if we have sane values.
	 * They're only really relevant if we're in Virtual Wire
	 * compatibility mode, but most boxes are anymore.
	 */
	reg0 = apic_read(APIC_LVT0);
	apic_printk(APIC_DEBUG, "Getting LVT0: %x\n", reg0);
	reg1 = apic_read(APIC_LVT1);
	apic_printk(APIC_DEBUG, "Getting LVT1: %x\n", reg1);

	return 1;
}

void __init sync_Arb_IDs(void)
{
	/* Unsupported on P4 - see Intel Dev. Manual Vol. 3, Ch. 8.6.1
	   And not needed on AMD */
	if (modern_apic())
		return;
	/*
	 * Wait for idle.
	 */
	apic_wait_icr_idle();

	apic_printk(APIC_DEBUG, "Synchronizing Arb IDs.\n");
	apic_write_around(APIC_ICR, APIC_DEST_ALLINC | APIC_INT_LEVELTRIG
				| APIC_DM_INIT);
}

extern void __error_in_apic_c (void);

/*
 * An initial setup of the virtual wire mode.
 */
void __init init_bsp_APIC(void)
{
	unsigned long value, ver;

	/*
	 * Don't do the setup now if we have a SMP BIOS as the
	 * through-I/O-APIC virtual wire mode might be active.
	 */
	if (smp_found_config || !cpu_has_apic)
		return;

	value = apic_read(APIC_LVR);
	ver = GET_APIC_VERSION(value);

	/*
	 * Do not trust the local APIC being empty at bootup.
	 */
	clear_local_APIC();

	/*
	 * Enable APIC.
	 */
	value = apic_read(APIC_SPIV);
	value &= ~APIC_VECTOR_MASK;
	value |= APIC_SPIV_APIC_ENABLED;
	
	/* This bit is reserved on P4/Xeon and should be cleared */
	if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && (boot_cpu_data.x86 == 15))
		value &= ~APIC_SPIV_FOCUS_DISABLED;
	else
		value |= APIC_SPIV_FOCUS_DISABLED;
	value |= SPURIOUS_APIC_VECTOR;
	apic_write_around(APIC_SPIV, value);

	/*
	 * Set up the virtual wire mode.
	 */
	apic_write_around(APIC_LVT0, APIC_DM_EXTINT);
	value = APIC_DM_NMI;
	if (!APIC_INTEGRATED(ver))		/* 82489DX */
		value |= APIC_LVT_LEVEL_TRIGGER;
	apic_write_around(APIC_LVT1, value);
}

void __devinit setup_local_APIC(void)
{
	unsigned long oldvalue, value, ver, maxlvt;
	int i, j;

	/* Pound the ESR really hard over the head with a big hammer - mbligh */
	if (esr_disable) {
		apic_write(APIC_ESR, 0);
		apic_write(APIC_ESR, 0);
		apic_write(APIC_ESR, 0);
		apic_write(APIC_ESR, 0);
	}

	value = apic_read(APIC_LVR);
	ver = GET_APIC_VERSION(value);

	if ((SPURIOUS_APIC_VECTOR & 0x0f) != 0x0f)
		__error_in_apic_c();

	/*
	 * Double-check whether this APIC is really registered.
	 */
	if (!apic_id_registered())
		BUG();

	/*
	 * Intel recommends to set DFR, LDR and TPR before enabling
	 * an APIC.  See e.g. "AP-388 82489DX User's Manual" (Intel
	 * document number 292116).  So here it goes...
	 */
	init_apic_ldr();

	/*
	 * Set Task Priority to 'accept all'. We never change this
	 * later on.
	 */
	value = apic_read(APIC_TASKPRI);
	value &= ~APIC_TPRI_MASK;
	apic_write_around(APIC_TASKPRI, value);

	/*
	 * After a crash, we no longer service the interrupts and a pending
	 * interrupt from previous kernel might still have ISR bit set.
	 *
	 * Most probably by now CPU has serviced that pending interrupt and
	 * it might not have done the ack_APIC_irq() because it thought,
	 * interrupt came from i8259 as ExtInt. LAPIC did not get EOI so it
	 * does not clear the ISR bit and cpu thinks it has already serivced
	 * the interrupt. Hence a vector might get locked. It was noticed
	 * for timer irq (vector 0x31). Issue an extra EOI to clear ISR.
	 */
	for (i = APIC_ISR_NR - 1; i >= 0; i--) {
		value = apic_read(APIC_ISR + i*0x10);
		for (j = 31; j >= 0; j--) {
			if (value & (1<<j))
				ack_APIC_irq();
		}
	}

	/*
	 * Now that we are all set up, enable the APIC
	 */
	value = apic_read(APIC_SPIV);
	value &= ~APIC_VECTOR_MASK;
	/*
	 * Enable APIC
	 */
	value |= APIC_SPIV_APIC_ENABLED;

	/*
	 * Some unknown Intel IO/APIC (or APIC) errata is biting us with
	 * certain networking cards. If high frequency interrupts are
	 * happening on a particular IOAPIC pin, plus the IOAPIC routing
	 * entry is masked/unmasked at a high rate as well then sooner or
	 * later IOAPIC line gets 'stuck', no more interrupts are received
	 * from the device. If focus CPU is disabled then the hang goes
	 * away, oh well :-(
	 *
	 * [ This bug can be reproduced easily with a level-triggered
	 *   PCI Ne2000 networking cards and PII/PIII processors, dual
	 *   BX chipset. ]
	 */
	/*
	 * Actually disabling the focus CPU check just makes the hang less
	 * frequent as it makes the interrupt distributon model be more
	 * like LRU than MRU (the short-term load is more even across CPUs).
	 * See also the comment in end_level_ioapic_irq().  --macro
	 */
#if 1
	/* Enable focus processor (bit==0) */
	value &= ~APIC_SPIV_FOCUS_DISABLED;
#else
	/* Disable focus processor (bit==1) */
	value |= APIC_SPIV_FOCUS_DISABLED;
#endif
	/*
	 * Set spurious IRQ vector
	 */
	value |= SPURIOUS_APIC_VECTOR;
	apic_write_around(APIC_SPIV, value);

	/*
	 * Set up LVT0, LVT1:
	 *
	 * set up through-local-APIC on the BP's LINT0. This is not
	 * strictly necessery in pure symmetric-IO mode, but sometimes
	 * we delegate interrupts to the 8259A.
	 */
	/*
	 * TODO: set up through-local-APIC from through-I/O-APIC? --macro
	 */
	value = apic_read(APIC_LVT0) & APIC_LVT_MASKED;
	if (!smp_processor_id() && (pic_mode || !value)) {
		value = APIC_DM_EXTINT;
		apic_printk(APIC_VERBOSE, "enabled ExtINT on CPU#%d\n",
				smp_processor_id());
	} else {
		value = APIC_DM_EXTINT | APIC_LVT_MASKED;
		apic_printk(APIC_VERBOSE, "masked ExtINT on CPU#%d\n",
				smp_processor_id());
	}
	apic_write_around(APIC_LVT0, value);

	/*
	 * only the BP should see the LINT1 NMI signal, obviously.
	 */
	if (!smp_processor_id())
		value = APIC_DM_NMI;
	else
		value = APIC_DM_NMI | APIC_LVT_MASKED;
	if (!APIC_INTEGRATED(ver))		/* 82489DX */
		value |= APIC_LVT_LEVEL_TRIGGER;
	apic_write_around(APIC_LVT1, value);

	if (APIC_INTEGRATED(ver) && !esr_disable) {		/* !82489DX */
		maxlvt = get_maxlvt();
		if (maxlvt > 3)		/* Due to the Pentium erratum 3AP. */
			apic_write(APIC_ESR, 0);
		oldvalue = apic_read(APIC_ESR);

		value = ERROR_APIC_VECTOR;      // enables sending errors
		apic_write_around(APIC_LVTERR, value);
		/*
		 * spec says clear errors after enabling vector.
		 */
		if (maxlvt > 3)
			apic_write(APIC_ESR, 0);
		value = apic_read(APIC_ESR);
		if (value != oldvalue)
			apic_printk(APIC_VERBOSE, "ESR value before enabling "
				"vector: 0x%08lx  after: 0x%08lx\n",
				oldvalue, value);
	} else {
		if (esr_disable)	
			/* 
			 * Something untraceble is creating bad interrupts on 
			 * secondary quads ... for the moment, just leave the
			 * ESR disabled - we can't do anything useful with the
			 * errors anyway - mbligh
			 */
			printk("Leaving ESR disabled.\n");
		else 
			printk("No ESR for 82489DX.\n");
	}

	setup_apic_nmi_watchdog(NULL);
	apic_pm_activate();
}

/*
 * If Linux enabled the LAPIC against the BIOS default
 * disable it down before re-entering the BIOS on shutdown.
 * Otherwise the BIOS may get confused and not power-off.
 * Additionally clear all LVT entries before disable_local_APIC
 * for the case where Linux didn't enable the LAPIC.
 */
void lapic_shutdown(void)
{
	unsigned long flags;

	if (!cpu_has_apic)
		return;

	local_irq_save(flags);
	clear_local_APIC();

	if (enabled_via_apicbase)
		disable_local_APIC();

	local_irq_restore(flags);
}

#ifdef CONFIG_PM

static struct {
	int active;
	/* r/w apic fields */
	unsigned int apic_id;
	unsigned int apic_taskpri;
	unsigned int apic_ldr;
	unsigned int apic_dfr;
	unsigned int apic_spiv;
	unsigned int apic_lvtt;
	unsigned int apic_lvtpc;
	unsigned int apic_lvt0;
	unsigned int apic_lvt1;
	unsigned int apic_lvterr;
	unsigned int apic_tmict;
	unsigned int apic_tdcr;
	unsigned int apic_thmr;
} apic_pm_state;

static int lapic_suspend(struct sys_device *dev, pm_message_t state)
{
	unsigned long flags;

	if (!apic_pm_state.active)
		return 0;

	apic_pm_state.apic_id = apic_read(APIC_ID);
	apic_pm_state.apic_taskpri = apic_read(APIC_TASKPRI);
	apic_pm_state.apic_ldr = apic_read(APIC_LDR);
	apic_pm_state.apic_dfr = apic_read(APIC_DFR);
	apic_pm_state.apic_spiv = apic_read(APIC_SPIV);
	apic_pm_state.apic_lvtt = apic_read(APIC_LVTT);
	apic_pm_state.apic_lvtpc = apic_read(APIC_LVTPC);
	apic_pm_state.apic_lvt0 = apic_read(APIC_LVT0);
	apic_pm_state.apic_lvt1 = apic_read(APIC_LVT1);
	apic_pm_state.apic_lvterr = apic_read(APIC_LVTERR);
	apic_pm_state.apic_tmict = apic_read(APIC_TMICT);
	apic_pm_state.apic_tdcr = apic_read(APIC_TDCR);
	apic_pm_state.apic_thmr = apic_read(APIC_LVTTHMR);
	
	local_irq_save(flags);
	disable_local_APIC();
	local_irq_restore(flags);
	return 0;
}

static int lapic_resume(struct sys_device *dev)
{
	unsigned int l, h;
	unsigned long flags;

	if (!apic_pm_state.active)
		return 0;

	local_irq_save(flags);

	/*
	 * Make sure the APICBASE points to the right address
	 *
	 * FIXME! This will be wrong if we ever support suspend on
	 * SMP! We'll need to do this as part of the CPU restore!
	 */
	rdmsr(MSR_IA32_APICBASE, l, h);
	l &= ~MSR_IA32_APICBASE_BASE;
	l |= MSR_IA32_APICBASE_ENABLE | mp_lapic_addr;
	wrmsr(MSR_IA32_APICBASE, l, h);

	apic_write(APIC_LVTERR, ERROR_APIC_VECTOR | APIC_LVT_MASKED);
	apic_write(APIC_ID, apic_pm_state.apic_id);
	apic_write(APIC_DFR, apic_pm_state.apic_dfr);
	apic_write(APIC_LDR, apic_pm_state.apic_ldr);
	apic_write(APIC_TASKPRI, apic_pm_state.apic_taskpri);
	apic_write(APIC_SPIV, apic_pm_state.apic_spiv);
	apic_write(APIC_LVT0, apic_pm_state.apic_lvt0);
	apic_write(APIC_LVT1, apic_pm_state.apic_lvt1);
	apic_write(APIC_LVTTHMR, apic_pm_state.apic_thmr);
	apic_write(APIC_LVTPC, apic_pm_state.apic_lvtpc);
	apic_write(APIC_LVTT, apic_pm_state.apic_lvtt);
	apic_write(APIC_TDCR, apic_pm_state.apic_tdcr);
	apic_write(APIC_TMICT, apic_pm_state.apic_tmict);
	apic_write(APIC_ESR, 0);
	apic_read(APIC_ESR);
	apic_write(APIC_LVTERR, apic_pm_state.apic_lvterr);
	apic_write(APIC_ESR, 0);
	apic_read(APIC_ESR);
	local_irq_restore(flags);
	return 0;
}

/*
 * This device has no shutdown method - fully functioning local APICs
 * are needed on every CPU up until machine_halt/restart/poweroff.
 */

static struct sysdev_class lapic_sysclass = {
	set_kset_name("lapic"),
	.resume		= lapic_resume,
	.suspend	= lapic_suspend,
};

static struct sys_device device_lapic = {
	.id	= 0,
	.cls	= &lapic_sysclass,
};

static void __devinit apic_pm_activate(void)
{
	apic_pm_state.active = 1;
}

static int __init init_lapic_sysfs(void)
{
	int error;

	if (!cpu_has_apic)
		return 0;
	/* XXX: remove suspend/resume procs if !apic_pm_state.active? */

	error = sysdev_class_register(&lapic_sysclass);
	if (!error)
		error = sysdev_register(&device_lapic);
	return error;
}
device_initcall(init_lapic_sysfs);

#else	/* CONFIG_PM */

static void apic_pm_activate(void) { }

#endif	/* CONFIG_PM */

/*
 * Detect and enable local APICs on non-SMP boards.
 * Original code written by Keir Fraser.
 */

static int __init apic_set_verbosity(char *str)
{
	if (strcmp("debug", str) == 0)
		apic_verbosity = APIC_DEBUG;
	else if (strcmp("verbose", str) == 0)
		apic_verbosity = APIC_VERBOSE;
	return 1;
}

__setup("apic=", apic_set_verbosity);

static int __init detect_init_APIC (void)
{
	u32 h, l, features;

	/* Disabled by kernel option? */
	if (enable_local_apic < 0)
		return -1;

	switch (boot_cpu_data.x86_vendor) {
	case X86_VENDOR_AMD:
		if ((boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model > 1) ||
		    (boot_cpu_data.x86 == 15))	    
			break;
		goto no_apic;
	case X86_VENDOR_INTEL:
		if (boot_cpu_data.x86 == 6 || boot_cpu_data.x86 == 15 ||
		    (boot_cpu_data.x86 == 5 && cpu_has_apic))
			break;
		goto no_apic;
	default:
		goto no_apic;
	}

	if (!cpu_has_apic) {
		/*
		 * Over-ride BIOS and try to enable the local
		 * APIC only if "lapic" specified.
		 */
		if (enable_local_apic <= 0) {
			printk("Local APIC disabled by BIOS -- "
			       "you can enable it with \"lapic\"\n");
			return -1;
		}
		/*
		 * Some BIOSes disable the local APIC in the
		 * APIC_BASE MSR. This can only be done in
		 * software for Intel P6 or later and AMD K7
		 * (Model > 1) or later.
		 */
		rdmsr(MSR_IA32_APICBASE, l, h);
		if (!(l & MSR_IA32_APICBASE_ENABLE)) {
			printk("Local APIC disabled by BIOS -- reenabling.\n");
			l &= ~MSR_IA32_APICBASE_BASE;
			l |= MSR_IA32_APICBASE_ENABLE | APIC_DEFAULT_PHYS_BASE;
			wrmsr(MSR_IA32_APICBASE, l, h);
			enabled_via_apicbase = 1;
		}
	}
	/*
	 * The APIC feature bit should now be enabled
	 * in `cpuid'
	 */
	features = cpuid_edx(1);
	if (!(features & (1 << X86_FEATURE_APIC))) {
		printk("Could not enable APIC!\n");
		return -1;
	}
	set_bit(X86_FEATURE_APIC, boot_cpu_data.x86_capability);
	mp_lapic_addr = APIC_DEFAULT_PHYS_BASE;

	/* The BIOS may have set up the APIC at some other address */
	rdmsr(MSR_IA32_APICBASE, l, h);
	if (l & MSR_IA32_APICBASE_ENABLE)
		mp_lapic_addr = l & MSR_IA32_APICBASE_BASE;

	if (nmi_watchdog != NMI_NONE)
		nmi_watchdog = NMI_LOCAL_APIC;

	printk("Found and enabled local APIC!\n");

	apic_pm_activate();

	return 0;

no_apic:
	printk("No local APIC present or hardware disabled\n");
	return -1;
}

void __init init_apic_mappings(void)
{
	unsigned long apic_phys;

	/*
	 * If no local APIC can be found then set up a fake all
	 * zeroes page to simulate the local APIC and another
	 * one for the IO-APIC.
	 */
	if (!smp_found_config && detect_init_APIC()) {
		apic_phys = (unsigned long) alloc_bootmem_pages(PAGE_SIZE);
		apic_phys = __pa(apic_phys);
	} else
		apic_phys = mp_lapic_addr;

	set_fixmap_nocache(FIX_APIC_BASE, apic_phys);
	printk(KERN_DEBUG "mapped APIC to %08lx (%08lx)\n", APIC_BASE,
	       apic_phys);

	/*
	 * Fetch the APIC ID of the BSP in case we have a
	 * default configuration (or the MP table is broken).
	 */
	if (boot_cpu_physical_apicid == -1U)
		boot_cpu_physical_apicid = GET_APIC_ID(apic_read(APIC_ID));

#ifdef CONFIG_X86_IO_APIC
	{
		unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0;
		int i;

		for (i = 0; i < nr_ioapics; i++) {
			if (smp_found_config) {
				ioapic_phys = mp_ioapics[i].mpc_apicaddr;
				if (!ioapic_phys) {
					printk(KERN_ERR
					       "WARNING: bogus zero IO-APIC "
					       "address found in MPTABLE, "
					       "disabling IO/APIC support!\n");
					smp_found_config = 0;
					skip_ioapic_setup = 1;
					goto fake_ioapic_page;
				}
			} else {
fake_ioapic_page:
				ioapic_phys = (unsigned long)
					      alloc_bootmem_pages(PAGE_SIZE);
				ioapic_phys = __pa(ioapic_phys);
			}
			set_fixmap_nocache(idx, ioapic_phys);
			printk(KERN_DEBUG "mapped IOAPIC to %08lx (%08lx)\n",
			       __fix_to_virt(idx), ioapic_phys);
			idx++;
		}
	}
#endif
}

/*
 * This part sets up the APIC 32 bit clock in LVTT1, with HZ interrupts
 * per second. We assume that the caller has already set up the local
 * APIC.
 *
 * The APIC timer is not exactly sync with the external timer chip, it
 * closely follows bus clocks.
 */

/*
 * The timer chip is already set up at HZ interrupts per second here,
 * but we do not accept timer interrupts yet. We only allow the BP
 * to calibrate.
 */
static unsigned int __devinit get_8254_timer_count(void)
{
	unsigned long flags;

	unsigned int count;

	spin_lock_irqsave(&i8253_lock, flags);

	outb_p(0x00, PIT_MODE);
	count = inb_p(PIT_CH0);
	count |= inb_p(PIT_CH0) << 8;

	spin_unlock_irqrestore(&i8253_lock, flags);

	return count;
}

/* next tick in 8254 can be caught by catching timer wraparound */
static void __devinit wait_8254_wraparound(void)
{
	unsigned int curr_count, prev_count;

	curr_count = get_8254_timer_count();
	do {
		prev_count = curr_count;
		curr_count = get_8254_timer_count();

		/* workaround for broken Mercury/Neptune */
		if (prev_count >= curr_count + 0x100)
			curr_count = get_8254_timer_count();

	} while (prev_count >= curr_count);
}

/*
 * Default initialization for 8254 timers. If we use other timers like HPET,
 * we override this later
 */
void (*wait_timer_tick)(void) __devinitdata = wait_8254_wraparound;

/*
 * This function sets up the local APIC timer, with a timeout of
 * 'clocks' APIC bus clock. During calibration we actually call
 * this function twice on the boot CPU, once with a bogus timeout
 * value, second time for real. The other (noncalibrating) CPUs
 * call this function only once, with the real, calibrated value.
 *
 * We do reads before writes even if unnecessary, to get around the
 * P5 APIC double write bug.
 */

#define APIC_DIVISOR 16

static void __setup_APIC_LVTT(unsigned int clocks)
{
	unsigned int lvtt_value, tmp_value, ver;
	int cpu = smp_processor_id();

	ver = GET_APIC_VERSION(apic_read(APIC_LVR));
	lvtt_value = APIC_LVT_TIMER_PERIODIC | LOCAL_TIMER_VECTOR;
	if (!APIC_INTEGRATED(ver))
		lvtt_value |= SET_APIC_TIMER_BASE(APIC_TIMER_BASE_DIV);

	if (cpu_isset(cpu, timer_bcast_ipi))
		lvtt_value |= APIC_LVT_MASKED;

	apic_write_around(APIC_LVTT, lvtt_value);

	/*
	 * Divide PICLK by 16
	 */
	tmp_value = apic_read(APIC_TDCR);
	apic_write_around(APIC_TDCR, (tmp_value
				& ~(APIC_TDR_DIV_1 | APIC_TDR_DIV_TMBASE))
				| APIC_TDR_DIV_16);

	apic_write_around(APIC_TMICT, clocks/APIC_DIVISOR);
}

static void __devinit setup_APIC_timer(unsigned int clocks)
{
	unsigned long flags;

	local_irq_save(flags);

	/*
	 * Wait for IRQ0's slice:
	 */
	wait_timer_tick();

	__setup_APIC_LVTT(clocks);

	local_irq_restore(flags);
}

/*
 * In this function we calibrate APIC bus clocks to the external
 * timer. Unfortunately we cannot use jiffies and the timer irq
 * to calibrate, since some later bootup code depends on getting
 * the first irq? Ugh.
 *
 * We want to do the calibration only once since we
 * want to have local timer irqs syncron. CPUs connected
 * by the same APIC bus have the very same bus frequency.
 * And we want to have irqs off anyways, no accidental
 * APIC irq that way.
 */

static int __init calibrate_APIC_clock(void)
{
	unsigned long long t1 = 0, t2 = 0;
	long tt1, tt2;
	long result;
	int i;
	const int LOOPS = HZ/10;

	apic_printk(APIC_VERBOSE, "calibrating APIC timer ...\n");

	/*
	 * Put whatever arbitrary (but long enough) timeout
	 * value into the APIC clock, we just want to get the
	 * counter running for calibration.
	 */
	__setup_APIC_LVTT(1000000000);

	/*
	 * The timer chip counts down to zero. Let's wait
	 * for a wraparound to start exact measurement:
	 * (the current tick might have been already half done)
	 */

	wait_timer_tick();

	/*
	 * We wrapped around just now. Let's start:
	 */
	if (cpu_has_tsc)
		rdtscll(t1);
	tt1 = apic_read(APIC_TMCCT);

	/*
	 * Let's wait LOOPS wraprounds:
	 */
	for (i = 0; i < LOOPS; i++)
		wait_timer_tick();

	tt2 = apic_read(APIC_TMCCT);
	if (cpu_has_tsc)
		rdtscll(t2);

	/*
	 * The APIC bus clock counter is 32 bits only, it
	 * might have overflown, but note that we use signed
	 * longs, thus no extra care needed.
	 *
	 * underflown to be exact, as the timer counts down ;)
	 */

	result = (tt1-tt2)*APIC_DIVISOR/LOOPS;

	if (cpu_has_tsc)
		apic_printk(APIC_VERBOSE, "..... CPU clock speed is "
			"%ld.%04ld MHz.\n",
			((long)(t2-t1)/LOOPS)/(1000000/HZ),
			((long)(t2-t1)/LOOPS)%(1000000/HZ));

	apic_printk(APIC_VERBOSE, "..... host bus clock speed is "
		"%ld.%04ld MHz.\n",
		result/(1000000/HZ),
		result%(1000000/HZ));

	return result;
}

static unsigned int calibration_result;

void __init setup_boot_APIC_clock(void)
{
	unsigned long flags;
	apic_printk(APIC_VERBOSE, "Using local APIC timer interrupts.\n");
	using_apic_timer = 1;

	local_irq_save(flags);

	calibration_result = calibrate_APIC_clock();
	/*
	 * Now set up the timer for real.
	 */
	setup_APIC_timer(calibration_result);

	local_irq_restore(flags);
}

void __devinit setup_secondary_APIC_clock(void)
{
	setup_APIC_timer(calibration_result);
}

void disable_APIC_timer(void)
{
	if (using_apic_timer) {
		unsigned long v;

		v = apic_read(APIC_LVTT);
		/*
		 * When an illegal vector value (0-15) is written to an LVT
		 * entry and delivery mode is Fixed, the APIC may signal an
		 * illegal vector error, with out regard to whether the mask
		 * bit is set or whether an interrupt is actually seen on input.
		 *
		 * Boot sequence might call this function when the LVTT has
		 * '0' vector value. So make sure vector field is set to
		 * valid value.
		 */
		v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
		apic_write_around(APIC_LVTT, v);
	}
}

void enable_APIC_timer(void)
{
	int cpu = smp_processor_id();

	if (using_apic_timer &&
	    !cpu_isset(cpu, timer_bcast_ipi)) {
		unsigned long v;

		v = apic_read(APIC_LVTT);
		apic_write_around(APIC_LVTT, v & ~APIC_LVT_MASKED);
	}
}

void switch_APIC_timer_to_ipi(void *cpumask)
{
	cpumask_t mask = *(cpumask_t *)cpumask;
	int cpu = smp_processor_id();

	if (cpu_isset(cpu, mask) &&
	    !cpu_isset(cpu, timer_bcast_ipi)) {
		disable_APIC_timer();
		cpu_set(cpu, timer_bcast_ipi);
	}
}
EXPORT_SYMBOL(switch_APIC_timer_to_ipi);

void switch_ipi_to_APIC_timer(void *cpumask)
{
	cpumask_t mask = *(cpumask_t *)cpumask;
	int cpu = smp_processor_id();

	if (cpu_isset(cpu, mask) &&
	    cpu_isset(cpu, timer_bcast_ipi)) {
		cpu_clear(cpu, timer_bcast_ipi);
		enable_APIC_timer();
	}
}
EXPORT_SYMBOL(switch_ipi_to_APIC_timer);

#undef APIC_DIVISOR

/*
 * Local timer interrupt handler. It does both profiling and
 * process statistics/rescheduling.
 *
 * We do profiling in every local tick, statistics/rescheduling
 * happen only every 'profiling multiplier' ticks. The default
 * multiplier is 1 and it can be changed by writing the new multiplier
 * value into /proc/profile.
 */

inline void smp_local_timer_interrupt(struct pt_regs * regs)
{
	profile_tick(CPU_PROFILING, regs);
#ifdef CONFIG_SMP
	update_process_times(user_mode_vm(regs));
#endif

	/*
	 * We take the 'long' return path, and there every subsystem
	 * grabs the apropriate locks (kernel lock/ irq lock).
	 *
	 * we might want to decouple profiling from the 'long path',
	 * and do the profiling totally in assembly.
	 *
	 * Currently this isn't too much of an issue (performance wise),
	 * we can take more than 100K local irqs per second on a 100 MHz P5.
	 */
}

/*
 * Local APIC timer interrupt. This is the most natural way for doing
 * local interrupts, but local timer interrupts can be emulated by
 * broadcast interrupts too. [in case the hw doesn't support APIC timers]
 *
 * [ if a single-CPU system runs an SMP kernel then we call the local
 *   interrupt as well. Thus we cannot inline the local irq ... ]
 */

fastcall void smp_apic_timer_interrupt(struct pt_regs *regs)
{
	int cpu = smp_processor_id();

	/*
	 * the NMI deadlock-detector uses this.
	 */
	per_cpu(irq_stat, cpu).apic_timer_irqs++;

	/*
	 * NOTE! We'd better ACK the irq immediately,
	 * because timer handling can be slow.
	 */
	ack_APIC_irq();
	/*
	 * update_process_times() expects us to have done irq_enter().
	 * Besides, if we don't timer interrupts ignore the global
	 * interrupt lock, which is the WrongThing (tm) to do.
	 */
	irq_enter();
	smp_local_timer_interrupt(regs);
	irq_exit();
}

#ifndef CONFIG_SMP
static void up_apic_timer_interrupt_call(struct pt_regs *regs)
{
	int cpu = smp_processor_id();

	/*
	 * the NMI deadlock-detector uses this.
	 */
	per_cpu(irq_stat, cpu).apic_timer_irqs++;

	smp_local_timer_interrupt(regs);
}
#endif

void smp_send_timer_broadcast_ipi(struct pt_regs *regs)
{
	cpumask_t mask;

	cpus_and(mask, cpu_online_map, timer_bcast_ipi);
	if (!cpus_empty(mask)) {
#ifdef CONFIG_SMP
		send_IPI_mask(mask, LOCAL_TIMER_VECTOR);
#else
		/*
		 * We can directly call the apic timer interrupt handler
		 * in UP case. Minus all irq related functions
		 */
		up_apic_timer_interrupt_call(regs);
#endif
	}
}

int setup_profiling_timer(unsigned int multiplier)
{
	return -EINVAL;
}

/*
 * This interrupt should _never_ happen with our APIC/SMP architecture
 */
fastcall void smp_spurious_interrupt(struct pt_regs *regs)
{
	unsigned long v;

	irq_enter();
	/*
	 * Check if this really is a spurious interrupt and ACK it
	 * if it is a vectored one.  Just in case...
	 * Spurious interrupts should not be ACKed.
	 */
	v = apic_read(APIC_ISR + ((SPURIOUS_APIC_VECTOR & ~0x1f) >> 1));
	if (v & (1 << (SPURIOUS_APIC_VECTOR & 0x1f)))
		ack_APIC_irq();

	/* see sw-dev-man vol 3, chapter 7.4.13.5 */
	printk(KERN_INFO "spurious APIC interrupt on CPU#%d, should never happen.\n",
			smp_processor_id());
	irq_exit();
}

/*
 * This interrupt should never happen with our APIC/SMP architecture
 */

fastcall void smp_error_interrupt(struct pt_regs *regs)
{
	unsigned long v, v1;

	irq_enter();
	/* First tickle the hardware, only then report what went on. -- REW */
	v = apic_read(APIC_ESR);
	apic_write(APIC_ESR, 0);
	v1 = apic_read(APIC_ESR);
	ack_APIC_irq();
	atomic_inc(&irq_err_count);

	/* Here is what the APIC error bits mean:
	   0: Send CS error
	   1: Receive CS error
	   2: Send accept error
	   3: Receive accept error
	   4: Reserved
	   5: Send illegal vector
	   6: Received illegal vector
	   7: Illegal register address
	*/
	printk (KERN_DEBUG "APIC error on CPU%d: %02lx(%02lx)\n",
	        smp_processor_id(), v , v1);
	irq_exit();
}

/*
 * This initializes the IO-APIC and APIC hardware if this is
 * a UP kernel.
 */
int __init APIC_init_uniprocessor (void)
{
	if (enable_local_apic < 0)
		clear_bit(X86_FEATURE_APIC, boot_cpu_data.x86_capability);

	if (!smp_found_config && !cpu_has_apic)
		return -1;

	/*
	 * Complain if the BIOS pretends there is one.
	 */
	if (!cpu_has_apic && APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) {
		printk(KERN_ERR "BIOS bug, local APIC #%d not detected!...\n",
			boot_cpu_physical_apicid);
		clear_bit(X86_FEATURE_APIC, boot_cpu_data.x86_capability);
		return -1;
	}

	verify_local_APIC();

	connect_bsp_APIC();

	/*
	 * Hack: In case of kdump, after a crash, kernel might be booting
	 * on a cpu with non-zero lapic id. But boot_cpu_physical_apicid
	 * might be zero if read from MP tables. Get it from LAPIC.
	 */
#ifdef CONFIG_CRASH_DUMP
	boot_cpu_physical_apicid = GET_APIC_ID(apic_read(APIC_ID));
#endif
	phys_cpu_present_map = physid_mask_of_physid(boot_cpu_physical_apicid);

	setup_local_APIC();

#ifdef CONFIG_X86_IO_APIC
	if (smp_found_config)
		if (!skip_ioapic_setup && nr_ioapics)
			setup_IO_APIC();
#endif
	setup_boot_APIC_clock();

	return 0;
}

static int __init parse_lapic(char *arg)
{
	lapic_enable();
	return 0;
}
early_param("lapic", parse_lapic);

static int __init parse_nolapic(char *arg)
{
	lapic_disable();
	return 0;
}
early_param("nolapic", parse_nolapic);

pt">[13]; /* status */ args[1] = desc[3]; /* error */ args[2] = desc[5]; /* sector count (0:7) */ args[3] = desc[7]; /* lbal */ args[4] = desc[9]; /* lbam */ args[5] = desc[11]; /* lbah */ args[6] = desc[12]; /* select */ if (copy_to_user(arg, args, sizeof(args))) rc = -EFAULT; } } if (cmd_result) { rc = -EIO; goto error; } error: kfree(sensebuf); return rc; } int ata_scsi_ioctl(struct scsi_device *scsidev, int cmd, void __user *arg) { int val = -EINVAL, rc = -EINVAL; switch (cmd) { case ATA_IOC_GET_IO32: val = 0; if (copy_to_user(arg, &val, 1)) return -EFAULT; return 0; case ATA_IOC_SET_IO32: val = (unsigned long) arg; if (val != 0) return -EINVAL; return 0; case HDIO_GET_IDENTITY: return ata_get_identity(scsidev, arg); case HDIO_DRIVE_CMD: if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO)) return -EACCES; return ata_cmd_ioctl(scsidev, arg); case HDIO_DRIVE_TASK: if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO)) return -EACCES; return ata_task_ioctl(scsidev, arg); default: rc = -ENOTTY; break; } return rc; } /** * ata_scsi_qc_new - acquire new ata_queued_cmd reference * @dev: ATA device to which the new command is attached * @cmd: SCSI command that originated this ATA command * @done: SCSI command completion function * * Obtain a reference to an unused ata_queued_cmd structure, * which is the basic libata structure representing a single * ATA command sent to the hardware. * * If a command was available, fill in the SCSI-specific * portions of the structure with information on the * current command. * * LOCKING: * spin_lock_irqsave(host lock) * * RETURNS: * Command allocated, or %NULL if none available. */ static struct ata_queued_cmd *ata_scsi_qc_new(struct ata_device *dev, struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *)) { struct ata_queued_cmd *qc; qc = ata_qc_new_init(dev); if (qc) { qc->scsicmd = cmd; qc->scsidone = done; if (cmd->use_sg) { qc->__sg = (struct scatterlist *) cmd->request_buffer; qc->n_elem = cmd->use_sg; } else if (cmd->request_bufflen) { qc->__sg = &qc->sgent; qc->n_elem = 1; } } else { cmd->result = (DID_OK << 16) | (QUEUE_FULL << 1); done(cmd); } return qc; } /** * ata_dump_status - user friendly display of error info * @id: id of the port in question * @tf: ptr to filled out taskfile * * Decode and dump the ATA error/status registers for the user so * that they have some idea what really happened at the non * make-believe layer. * * LOCKING: * inherited from caller */ static void ata_dump_status(unsigned id, struct ata_taskfile *tf) { u8 stat = tf->command, err = tf->feature; printk(KERN_WARNING "ata%u: status=0x%02x { ", id, stat); if (stat & ATA_BUSY) { printk("Busy }\n"); /* Data is not valid in this case */ } else { if (stat & 0x40) printk("DriveReady "); if (stat & 0x20) printk("DeviceFault "); if (stat & 0x10) printk("SeekComplete "); if (stat & 0x08) printk("DataRequest "); if (stat & 0x04) printk("CorrectedError "); if (stat & 0x02) printk("Index "); if (stat & 0x01) printk("Error "); printk("}\n"); if (err) { printk(KERN_WARNING "ata%u: error=0x%02x { ", id, err); if (err & 0x04) printk("DriveStatusError "); if (err & 0x80) { if (err & 0x04) printk("BadCRC "); else printk("Sector "); } if (err & 0x40) printk("UncorrectableError "); if (err & 0x10) printk("SectorIdNotFound "); if (err & 0x02) printk("TrackZeroNotFound "); if (err & 0x01) printk("AddrMarkNotFound "); printk("}\n"); } } } #ifdef CONFIG_PM /** * ata_scsi_device_suspend - suspend ATA device associated with sdev * @sdev: the SCSI device to suspend * @mesg: target power management message * * Request suspend EH action on the ATA device associated with * @sdev and wait for the operation to complete. * * LOCKING: * Kernel thread context (may sleep). * * RETURNS: * 0 on success, -errno otherwise. */ int ata_scsi_device_suspend(struct scsi_device *sdev, pm_message_t mesg) { struct ata_port *ap = ata_shost_to_port(sdev->host); struct ata_device *dev = ata_scsi_find_dev(ap, sdev); unsigned long flags; unsigned int action; int rc = 0; if (!dev) goto out; spin_lock_irqsave(ap->lock, flags); /* wait for the previous resume to complete */ while (dev->flags & ATA_DFLAG_SUSPENDED) { spin_unlock_irqrestore(ap->lock, flags); ata_port_wait_eh(ap); spin_lock_irqsave(ap->lock, flags); } /* if @sdev is already detached, nothing to do */ if (sdev->sdev_state == SDEV_OFFLINE || sdev->sdev_state == SDEV_CANCEL || sdev->sdev_state == SDEV_DEL) goto out_unlock; /* request suspend */ action = ATA_EH_SUSPEND; if (mesg.event != PM_EVENT_SUSPEND) action |= ATA_EH_PM_FREEZE; ap->eh_info.dev_action[dev->devno] |= action; ap->eh_info.flags |= ATA_EHI_QUIET; ata_port_schedule_eh(ap); spin_unlock_irqrestore(ap->lock, flags); /* wait for EH to do the job */ ata_port_wait_eh(ap); spin_lock_irqsave(ap->lock, flags); /* If @sdev is still attached but the associated ATA device * isn't suspended, the operation failed. */ if (sdev->sdev_state != SDEV_OFFLINE && sdev->sdev_state != SDEV_CANCEL && sdev->sdev_state != SDEV_DEL && !(dev->flags & ATA_DFLAG_SUSPENDED)) rc = -EIO; out_unlock: spin_unlock_irqrestore(ap->lock, flags); out: if (rc == 0) sdev->sdev_gendev.power.power_state = mesg; return rc; } /** * ata_scsi_device_resume - resume ATA device associated with sdev * @sdev: the SCSI device to resume * * Request resume EH action on the ATA device associated with * @sdev and return immediately. This enables parallel * wakeup/spinup of devices. * * LOCKING: * Kernel thread context (may sleep). * * RETURNS: * 0. */ int ata_scsi_device_resume(struct scsi_device *sdev) { struct ata_port *ap = ata_shost_to_port(sdev->host); struct ata_device *dev = ata_scsi_find_dev(ap, sdev); struct ata_eh_info *ehi = &ap->eh_info; unsigned long flags; unsigned int action; if (!dev) goto out; spin_lock_irqsave(ap->lock, flags); /* if @sdev is already detached, nothing to do */ if (sdev->sdev_state == SDEV_OFFLINE || sdev->sdev_state == SDEV_CANCEL || sdev->sdev_state == SDEV_DEL) goto out_unlock; /* request resume */ action = ATA_EH_RESUME; if (sdev->sdev_gendev.power.power_state.event == PM_EVENT_SUSPEND) __ata_ehi_hotplugged(ehi); else action |= ATA_EH_PM_FREEZE | ATA_EH_SOFTRESET; ehi->dev_action[dev->devno] |= action; /* We don't want autopsy and verbose EH messages. Disable * those if we're the only device on this link. */ if (ata_port_max_devices(ap) == 1) ehi->flags |= ATA_EHI_NO_AUTOPSY | ATA_EHI_QUIET; ata_port_schedule_eh(ap); out_unlock: spin_unlock_irqrestore(ap->lock, flags); out: sdev->sdev_gendev.power.power_state = PMSG_ON; return 0; } #endif /* CONFIG_PM */ /** * ata_to_sense_error - convert ATA error to SCSI error * @id: ATA device number * @drv_stat: value contained in ATA status register * @drv_err: value contained in ATA error register * @sk: the sense key we'll fill out * @asc: the additional sense code we'll fill out * @ascq: the additional sense code qualifier we'll fill out * @verbose: be verbose * * Converts an ATA error into a SCSI error. Fill out pointers to * SK, ASC, and ASCQ bytes for later use in fixed or descriptor * format sense blocks. * * LOCKING: * spin_lock_irqsave(host lock) */ static void ata_to_sense_error(unsigned id, u8 drv_stat, u8 drv_err, u8 *sk, u8 *asc, u8 *ascq, int verbose) { int i; /* Based on the 3ware driver translation table */ static const unsigned char sense_table[][4] = { /* BBD|ECC|ID|MAR */ {0xd1, ABORTED_COMMAND, 0x00, 0x00}, // Device busy Aborted command /* BBD|ECC|ID */ {0xd0, ABORTED_COMMAND, 0x00, 0x00}, // Device busy Aborted command /* ECC|MC|MARK */ {0x61, HARDWARE_ERROR, 0x00, 0x00}, // Device fault Hardware error /* ICRC|ABRT */ /* NB: ICRC & !ABRT is BBD */ {0x84, ABORTED_COMMAND, 0x47, 0x00}, // Data CRC error SCSI parity error /* MC|ID|ABRT|TRK0|MARK */ {0x37, NOT_READY, 0x04, 0x00}, // Unit offline Not ready /* MCR|MARK */ {0x09, NOT_READY, 0x04, 0x00}, // Unrecovered disk error Not ready /* Bad address mark */ {0x01, MEDIUM_ERROR, 0x13, 0x00}, // Address mark not found Address mark not found for data field /* TRK0 */ {0x02, HARDWARE_ERROR, 0x00, 0x00}, // Track 0 not found Hardware error /* Abort & !ICRC */ {0x04, ABORTED_COMMAND, 0x00, 0x00}, // Aborted command Aborted command /* Media change request */ {0x08, NOT_READY, 0x04, 0x00}, // Media change request FIXME: faking offline /* SRV */ {0x10, ABORTED_COMMAND, 0x14, 0x00}, // ID not found Recorded entity not found /* Media change */ {0x08, NOT_READY, 0x04, 0x00}, // Media change FIXME: faking offline /* ECC */ {0x40, MEDIUM_ERROR, 0x11, 0x04}, // Uncorrectable ECC error Unrecovered read error /* BBD - block marked bad */ {0x80, MEDIUM_ERROR, 0x11, 0x04}, // Block marked bad Medium error, unrecovered read error {0xFF, 0xFF, 0xFF, 0xFF}, // END mark }; static const unsigned char stat_table[][4] = { /* Must be first because BUSY means no other bits valid */ {0x80, ABORTED_COMMAND, 0x47, 0x00}, // Busy, fake parity for now {0x20, HARDWARE_ERROR, 0x00, 0x00}, // Device fault {0x08, ABORTED_COMMAND, 0x47, 0x00}, // Timed out in xfer, fake parity for now {0x04, RECOVERED_ERROR, 0x11, 0x00}, // Recovered ECC error Medium error, recovered {0xFF, 0xFF, 0xFF, 0xFF}, // END mark }; /* * Is this an error we can process/parse */ if (drv_stat & ATA_BUSY) { drv_err = 0; /* Ignore the err bits, they're invalid */ } if (drv_err) { /* Look for drv_err */ for (i = 0; sense_table[i][0] != 0xFF; i++) { /* Look for best matches first */ if ((sense_table[i][0] & drv_err) == sense_table[i][0]) { *sk = sense_table[i][1]; *asc = sense_table[i][2]; *ascq = sense_table[i][3]; goto translate_done; } } /* No immediate match */ if (verbose) printk(KERN_WARNING "ata%u: no sense translation for " "error 0x%02x\n", id, drv_err); } /* Fall back to interpreting status bits */ for (i = 0; stat_table[i][0] != 0xFF; i++) { if (stat_table[i][0] & drv_stat) { *sk = stat_table[i][1]; *asc = stat_table[i][2]; *ascq = stat_table[i][3]; goto translate_done; } } /* No error? Undecoded? */ if (verbose) printk(KERN_WARNING "ata%u: no sense translation for " "status: 0x%02x\n", id, drv_stat); /* We need a sensible error return here, which is tricky, and one that won't cause people to do things like return a disk wrongly */ *sk = ABORTED_COMMAND; *asc = 0x00; *ascq = 0x00; translate_done: if (verbose) printk(KERN_ERR "ata%u: translated ATA stat/err 0x%02x/%02x " "to SCSI SK/ASC/ASCQ 0x%x/%02x/%02x\n", id, drv_stat, drv_err, *sk, *asc, *ascq); return; } /* * ata_gen_passthru_sense - Generate check condition sense block. * @qc: Command that completed. * * This function is specific to the ATA descriptor format sense * block specified for the ATA pass through commands. Regardless * of whether the command errored or not, return a sense * block. Copy all controller registers into the sense * block. Clear sense key, ASC & ASCQ if there is no error. * * LOCKING: * None. */ static void ata_gen_passthru_sense(struct ata_queued_cmd *qc) { struct scsi_cmnd *cmd = qc->scsicmd; struct ata_taskfile *tf = &qc->result_tf; unsigned char *sb = cmd->sense_buffer; unsigned char *desc = sb + 8; int verbose = qc->ap->ops->error_handler == NULL; memset(sb, 0, SCSI_SENSE_BUFFERSIZE); cmd->result = (DRIVER_SENSE << 24) | SAM_STAT_CHECK_CONDITION; /* * Use ata_to_sense_error() to map status register bits * onto sense key, asc & ascq. */ if (qc->err_mask || tf->command & (ATA_BUSY | ATA_DF | ATA_ERR | ATA_DRQ)) { ata_to_sense_error(qc->ap->print_id, tf->command, tf->feature, &sb[1], &sb[2], &sb[3], verbose); sb[1] &= 0x0f; } /* * Sense data is current and format is descriptor. */ sb[0] = 0x72; desc[0] = 0x09; /* set length of additional sense data */ sb[7] = 14; desc[1] = 12; /* * Copy registers into sense buffer. */ desc[2] = 0x00; desc[3] = tf->feature; /* == error reg */ desc[5] = tf->nsect; desc[7] = tf->lbal; desc[9] = tf->lbam; desc[11] = tf->lbah; desc[12] = tf->device; desc[13] = tf->command; /* == status reg */ /* * Fill in Extend bit, and the high order bytes * if applicable. */ if (tf->flags & ATA_TFLAG_LBA48) { desc[2] |= 0x01; desc[4] = tf->hob_nsect; desc[6] = tf->hob_lbal; desc[8] = tf->hob_lbam; desc[10] = tf->hob_lbah; } } /** * ata_gen_ata_sense - generate a SCSI fixed sense block * @qc: Command that we are erroring out * * Generate sense block for a failed ATA command @qc. Descriptor * format is used to accomodate LBA48 block address. * * LOCKING: * None. */ static void ata_gen_ata_sense(struct ata_queued_cmd *qc) { struct ata_device *dev = qc->dev; struct scsi_cmnd *cmd = qc->scsicmd; struct ata_taskfile *tf = &qc->result_tf; unsigned char *sb = cmd->sense_buffer; unsigned char *desc = sb + 8; int verbose = qc->ap->ops->error_handler == NULL; u64 block; memset(sb, 0, SCSI_SENSE_BUFFERSIZE); cmd->result = (DRIVER_SENSE << 24) | SAM_STAT_CHECK_CONDITION; /* sense data is current and format is descriptor */ sb[0] = 0x72; /* Use ata_to_sense_error() to map status register bits * onto sense key, asc & ascq. */ if (qc->err_mask || tf->command & (ATA_BUSY | ATA_DF | ATA_ERR | ATA_DRQ)) { ata_to_sense_error(qc->ap->print_id, tf->command, tf->feature, &sb[1], &sb[2], &sb[3], verbose); sb[1] &= 0x0f; } block = ata_tf_read_block(&qc->result_tf, dev); /* information sense data descriptor */ sb[7] = 12; desc[0] = 0x00; desc[1] = 10; desc[2] |= 0x80; /* valid */ desc[6] = block >> 40; desc[7] = block >> 32; desc[8] = block >> 24; desc[9] = block >> 16; desc[10] = block >> 8; desc[11] = block; } static void ata_scsi_sdev_config(struct scsi_device *sdev) { sdev->use_10_for_rw = 1; sdev->use_10_for_ms = 1; } static void ata_scsi_dev_config(struct scsi_device *sdev, struct ata_device *dev) { /* configure max sectors */ blk_queue_max_sectors(sdev->request_queue, dev->max_sectors); /* SATA DMA transfers must be multiples of 4 byte, so * we need to pad ATAPI transfers using an extra sg. * Decrement max hw segments accordingly. */ if (dev->class == ATA_DEV_ATAPI) { request_queue_t *q = sdev->request_queue; blk_queue_max_hw_segments(q, q->max_hw_segments - 1); } if (dev->flags & ATA_DFLAG_NCQ) { int depth; depth = min(sdev->host->can_queue, ata_id_queue_depth(dev->id)); depth = min(ATA_MAX_QUEUE - 1, depth); scsi_adjust_queue_depth(sdev, MSG_SIMPLE_TAG, depth); } } /** * ata_scsi_slave_config - Set SCSI device attributes * @sdev: SCSI device to examine * * This is called before we actually start reading * and writing to the device, to configure certain * SCSI mid-layer behaviors. * * LOCKING: * Defined by SCSI layer. We don't really care. */ int ata_scsi_slave_config(struct scsi_device *sdev) { struct ata_port *ap = ata_shost_to_port(sdev->host); struct ata_device *dev = __ata_scsi_find_dev(ap, sdev); ata_scsi_sdev_config(sdev); blk_queue_max_phys_segments(sdev->request_queue, LIBATA_MAX_PRD); if (dev) ata_scsi_dev_config(sdev, dev); return 0; /* scsi layer doesn't check return value, sigh */ } /** * ata_scsi_slave_destroy - SCSI device is about to be destroyed * @sdev: SCSI device to be destroyed * * @sdev is about to be destroyed for hot/warm unplugging. If * this unplugging was initiated by libata as indicated by NULL * dev->sdev, this function doesn't have to do anything. * Otherwise, SCSI layer initiated warm-unplug is in progress. * Clear dev->sdev, schedule the device for ATA detach and invoke * EH. * * LOCKING: * Defined by SCSI layer. We don't really care. */ void ata_scsi_slave_destroy(struct scsi_device *sdev) { struct ata_port *ap = ata_shost_to_port(sdev->host); unsigned long flags; struct ata_device *dev; if (!ap->ops->error_handler) return; spin_lock_irqsave(ap->lock, flags); dev = __ata_scsi_find_dev(ap, sdev); if (dev && dev->sdev) { /* SCSI device already in CANCEL state, no need to offline it */ dev->sdev = NULL; dev->flags |= ATA_DFLAG_DETACH; ata_port_schedule_eh(ap); } spin_unlock_irqrestore(ap->lock, flags); } /** * ata_scsi_change_queue_depth - SCSI callback for queue depth config * @sdev: SCSI device to configure queue depth for * @queue_depth: new queue depth * * This is libata standard hostt->change_queue_depth callback. * SCSI will call into this callback when user tries to set queue * depth via sysfs. * * LOCKING: * SCSI layer (we don't care) * * RETURNS: * Newly configured queue depth. */ int ata_scsi_change_queue_depth(struct scsi_device *sdev, int queue_depth) { struct ata_port *ap = ata_shost_to_port(sdev->host); struct ata_device *dev; unsigned long flags; if (queue_depth < 1 || queue_depth == sdev->queue_depth) return sdev->queue_depth; dev = ata_scsi_find_dev(ap, sdev); if (!dev || !ata_dev_enabled(dev)) return sdev->queue_depth; /* NCQ enabled? */ spin_lock_irqsave(ap->lock, flags); dev->flags &= ~ATA_DFLAG_NCQ_OFF; if (queue_depth == 1 || !ata_ncq_enabled(dev)) { dev->flags |= ATA_DFLAG_NCQ_OFF; queue_depth = 1; } spin_unlock_irqrestore(ap->lock, flags); /* limit and apply queue depth */ queue_depth = min(queue_depth, sdev->host->can_queue); queue_depth = min(queue_depth, ata_id_queue_depth(dev->id)); queue_depth = min(queue_depth, ATA_MAX_QUEUE - 1); if (sdev->queue_depth == queue_depth) return -EINVAL; scsi_adjust_queue_depth(sdev, MSG_SIMPLE_TAG, queue_depth); return queue_depth; } /** * ata_scsi_start_stop_xlat - Translate SCSI START STOP UNIT command * @qc: Storage for translated ATA taskfile * * Sets up an ATA taskfile to issue STANDBY (to stop) or READ VERIFY * (to start). Perhaps these commands should be preceded by * CHECK POWER MODE to see what power mode the device is already in. * [See SAT revision 5 at www.t10.org] * * LOCKING: * spin_lock_irqsave(host lock) * * RETURNS: * Zero on success, non-zero on error. */ static unsigned int ata_scsi_start_stop_xlat(struct ata_queued_cmd *qc) { struct scsi_cmnd *scmd = qc->scsicmd; struct ata_taskfile *tf = &qc->tf; const u8 *cdb = scmd->cmnd; if (scmd->cmd_len < 5) goto invalid_fld; tf->flags |= ATA_TFLAG_DEVICE | ATA_TFLAG_ISADDR; tf->protocol = ATA_PROT_NODATA; if (cdb[1] & 0x1) { ; /* ignore IMMED bit, violates sat-r05 */ } if (cdb[4] & 0x2) goto invalid_fld; /* LOEJ bit set not supported */ if (((cdb[4] >> 4) & 0xf) != 0) goto invalid_fld; /* power conditions not supported */ if (cdb[4] & 0x1) { tf->nsect = 1; /* 1 sector, lba=0 */ if (qc->dev->flags & ATA_DFLAG_LBA) { tf->flags |= ATA_TFLAG_LBA; tf->lbah = 0x0; tf->lbam = 0x0; tf->lbal = 0x0; tf->device |= ATA_LBA; } else { /* CHS */ tf->lbal = 0x1; /* sect */ tf->lbam = 0x0; /* cyl low */ tf->lbah = 0x0; /* cyl high */ } tf->command = ATA_CMD_VERIFY; /* READ VERIFY */ } else /* Issue ATA STANDBY IMMEDIATE command */ tf->command = ATA_CMD_STANDBYNOW1; /* * Standby and Idle condition timers could be implemented but that * would require libata to implement the Power condition mode page * and allow the user to change it. Changing mode pages requires * MODE SELECT to be implemented. */ return 0; invalid_fld: ata_scsi_set_sense(scmd, ILLEGAL_REQUEST, 0x24, 0x0); /* "Invalid field in cbd" */ return 1; } /** * ata_scsi_flush_xlat - Translate SCSI SYNCHRONIZE CACHE command * @qc: Storage for translated ATA taskfile * * Sets up an ATA taskfile to issue FLUSH CACHE or * FLUSH CACHE EXT. * * LOCKING: * spin_lock_irqsave(host lock) * * RETURNS: * Zero on success, non-zero on error. */ static unsigned int ata_scsi_flush_xlat(struct ata_queued_cmd *qc) { struct ata_taskfile *tf = &qc->tf; tf->flags |= ATA_TFLAG_DEVICE; tf->protocol = ATA_PROT_NODATA; if (qc->dev->flags & ATA_DFLAG_FLUSH_EXT) tf->command = ATA_CMD_FLUSH_EXT; else tf->command = ATA_CMD_FLUSH; return 0; } /** * scsi_6_lba_len - Get LBA and transfer length * @cdb: SCSI command to translate * * Calculate LBA and transfer length for 6-byte commands. * * RETURNS: * @plba: the LBA * @plen: the transfer length */ static void scsi_6_lba_len(const u8 *cdb, u64 *plba, u32 *plen) { u64 lba = 0; u32 len = 0; VPRINTK("six-byte command\n"); lba |= ((u64)cdb[2]) << 8; lba |= ((u64)cdb[3]); len |= ((u32)cdb[4]); *plba = lba; *plen = len; } /** * scsi_10_lba_len - Get LBA and transfer length * @cdb: SCSI command to translate * * Calculate LBA and transfer length for 10-byte commands. * * RETURNS: * @plba: the LBA * @plen: the transfer length */ static void scsi_10_lba_len(const u8 *cdb, u64 *plba, u32 *plen) { u64 lba = 0; u32 len = 0; VPRINTK("ten-byte command\n"); lba |= ((u64)cdb[2]) << 24; lba |= ((u64)cdb[3]) << 16; lba |= ((u64)cdb[4]) << 8; lba |= ((u64)cdb[5]); len |= ((u32)cdb[7]) << 8; len |= ((u32)cdb[8]); *plba = lba; *plen = len; } /** * scsi_16_lba_len - Get LBA and transfer length * @cdb: SCSI command to translate * * Calculate LBA and transfer length for 16-byte commands. * * RETURNS: * @plba: the LBA * @plen: the transfer length */ static void scsi_16_lba_len(const u8 *cdb, u64 *plba, u32 *plen) { u64 lba = 0; u32 len = 0; VPRINTK("sixteen-byte command\n"); lba |= ((u64)cdb[2]) << 56; lba |= ((u64)cdb[3]) << 48; lba |= ((u64)cdb[4]) << 40; lba |= ((u64)cdb[5]) << 32; lba |= ((u64)cdb[6]) << 24; lba |= ((u64)cdb[7]) << 16; lba |= ((u64)cdb[8]) << 8; lba |= ((u64)cdb[9]); len |= ((u32)cdb[10]) << 24; len |= ((u32)cdb[11]) << 16; len |= ((u32)cdb[12]) << 8; len |= ((u32)cdb[13]); *plba = lba; *plen = len; } /** * ata_scsi_verify_xlat - Translate SCSI VERIFY command into an ATA one * @qc: Storage for translated ATA taskfile * * Converts SCSI VERIFY command to an ATA READ VERIFY command. * * LOCKING: * spin_lock_irqsave(host lock) * * RETURNS: * Zero on success, non-zero on error. */ static unsigned int ata_scsi_verify_xlat(struct ata_queued_cmd *qc) { struct scsi_cmnd *scmd = qc->scsicmd; struct ata_taskfile *tf = &qc->tf; struct ata_device *dev = qc->dev; u64 dev_sectors = qc->dev->n_sectors; const u8 *cdb = scmd->cmnd; u64 block; u32 n_block; tf->flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE; tf->protocol = ATA_PROT_NODATA; if (cdb[0] == VERIFY) { if (scmd->cmd_len < 10) goto invalid_fld; scsi_10_lba_len(cdb, &block, &n_block); } else if (cdb[0] == VERIFY_16) { if (scmd->cmd_len < 16) goto invalid_fld; scsi_16_lba_len(cdb, &block, &n_block); } else goto invalid_fld; if (!n_block) goto nothing_to_do; if (block >= dev_sectors) goto out_of_range; if ((block + n_block) > dev_sectors) goto out_of_range; if (dev->flags & ATA_DFLAG_LBA) { tf->flags |= ATA_TFLAG_LBA; if (lba_28_ok(block, n_block)) { /* use LBA28 */ tf->command = ATA_CMD_VERIFY; tf->device |= (block >> 24) & 0xf; } else if (lba_48_ok(block, n_block)) { if (!(dev->flags & ATA_DFLAG_LBA48)) goto out_of_range; /* use LBA48 */ tf->flags |= ATA_TFLAG_LBA48; tf->command = ATA_CMD_VERIFY_EXT; tf->hob_nsect = (n_block >> 8) & 0xff; tf->hob_lbah = (block >> 40) & 0xff; tf->hob_lbam = (block >> 32) & 0xff; tf->hob_lbal = (block >> 24) & 0xff; } else /* request too large even for LBA48 */ goto out_of_range; tf->nsect = n_block & 0xff; tf->lbah = (block >> 16) & 0xff; tf->lbam = (block >> 8) & 0xff; tf->lbal = block & 0xff; tf->device |= ATA_LBA; } else { /* CHS */ u32 sect, head, cyl, track; if (!lba_28_ok(block, n_block)) goto out_of_range; /* Convert LBA to CHS */ track = (u32)block / dev->sectors; cyl = track / dev->heads; head = track % dev->heads; sect = (u32)block % dev->sectors + 1; DPRINTK("block %u track %u cyl %u head %u sect %u\n", (u32)block, track, cyl, head, sect); /* Check whether the converted CHS can fit. Cylinder: 0-65535 Head: 0-15 Sector: 1-255*/ if ((cyl >> 16) || (head >> 4) || (sect >> 8) || (!sect)) goto out_of_range; tf->command = ATA_CMD_VERIFY; tf->nsect = n_block & 0xff; /* Sector count 0 means 256 sectors */ tf->lbal = sect; tf->lbam = cyl; tf->lbah = cyl >> 8; tf->device |= head; } return 0; invalid_fld: ata_scsi_set_sense(scmd, ILLEGAL_REQUEST, 0x24, 0x0); /* "Invalid field in cbd" */ return 1; out_of_range: ata_scsi_set_sense(scmd, ILLEGAL_REQUEST, 0x21, 0x0); /* "Logical Block Address out of range" */ return 1; nothing_to_do: scmd->result = SAM_STAT_GOOD; return 1; } /** * ata_scsi_rw_xlat - Translate SCSI r/w command into an ATA one * @qc: Storage for translated ATA taskfile * * Converts any of six SCSI read/write commands into the * ATA counterpart, including starting sector (LBA), * sector count, and taking into account the device's LBA48 * support. * * Commands %READ_6, %READ_10, %READ_16, %WRITE_6, %WRITE_10, and * %WRITE_16 are currently supported. * * LOCKING: * spin_lock_irqsave(host lock) * * RETURNS: * Zero on success, non-zero on error. */ static unsigned int ata_scsi_rw_xlat(struct ata_queued_cmd *qc) { struct scsi_cmnd *scmd = qc->scsicmd; const u8 *cdb = scmd->cmnd; unsigned int tf_flags = 0; u64 block; u32 n_block; int rc; if (cdb[0] == WRITE_10 || cdb[0] == WRITE_6 || cdb[0] == WRITE_16) tf_flags |= ATA_TFLAG_WRITE; /* Calculate the SCSI LBA, transfer length and FUA. */ switch (cdb[0]) { case READ_10: case WRITE_10: if (unlikely(scmd->cmd_len < 10)) goto invalid_fld; scsi_10_lba_len(cdb, &block, &n_block); if (unlikely(cdb[1] & (1 << 3))) tf_flags |= ATA_TFLAG_FUA; break; case READ_6: case WRITE_6: if (unlikely(scmd->cmd_len < 6)) goto invalid_fld; scsi_6_lba_len(cdb, &block, &n_block); /* for 6-byte r/w commands, transfer length 0 * means 256 blocks of data, not 0 block. */ if (!n_block) n_block = 256; break; case READ_16: case WRITE_16: if (unlikely(scmd->cmd_len < 16)) goto invalid_fld; scsi_16_lba_len(cdb, &block, &n_block); if (unlikely(cdb[1] & (1 << 3))) tf_flags |= ATA_TFLAG_FUA; break; default: DPRINTK("no-byte command\n"); goto invalid_fld; } /* Check and compose ATA command */ if (!n_block) /* For 10-byte and 16-byte SCSI R/W commands, transfer * length 0 means transfer 0 block of data. * However, for ATA R/W commands, sector count 0 means * 256 or 65536 sectors, not 0 sectors as in SCSI. * * WARNING: one or two older ATA drives treat 0 as 0... */ goto nothing_to_do; qc->flags |= ATA_QCFLAG_IO; qc->nbytes = n_block * ATA_SECT_SIZE; rc = ata_build_rw_tf(&qc->tf, qc->dev, block, n_block, tf_flags, qc->tag); if (likely(rc == 0)) return 0; if (rc == -ERANGE) goto out_of_range; /* treat all other errors as -EINVAL, fall through */ invalid_fld: ata_scsi_set_sense(scmd, ILLEGAL_REQUEST, 0x24, 0x0); /* "Invalid field in cbd" */ return 1; out_of_range: ata_scsi_set_sense(scmd, ILLEGAL_REQUEST, 0x21, 0x0); /* "Logical Block Address out of range" */ return 1; nothing_to_do: scmd->result = SAM_STAT_GOOD; return 1; } static void ata_scsi_qc_complete(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct scsi_cmnd *cmd = qc->scsicmd; u8 *cdb = cmd->cmnd; int need_sense = (qc->err_mask != 0); /* We snoop the SET_FEATURES - Write Cache ON/OFF command, and * schedule EH_REVALIDATE operation to update the IDENTIFY DEVICE * cache */ if (ap->ops->error_handler && !need_sense && (qc->tf.command == ATA_CMD_SET_FEATURES) && ((qc->tf.feature == SETFEATURES_WC_ON) || (qc->tf.feature == SETFEATURES_WC_OFF))) { ap->eh_info.action |= ATA_EH_REVALIDATE; ata_port_schedule_eh(ap); } /* For ATA pass thru (SAT) commands, generate a sense block if * user mandated it or if there's an error. Note that if we * generate because the user forced us to, a check condition * is generated and the ATA register values are returned * whether the command completed successfully or not. If there * was no error, SK, ASC and ASCQ will all be zero. */ if (((cdb[0] == ATA_16) || (cdb[0] == ATA_12)) && ((cdb[2] & 0x20) || need_sense)) { ata_gen_passthru_sense(qc); } else { if (!need_sense) { cmd->result = SAM_STAT_GOOD; } else { /* TODO: decide which descriptor format to use * for 48b LBA devices and call that here * instead of the fixed desc, which is only * good for smaller LBA (and maybe CHS?) * devices. */ ata_gen_ata_sense(qc); } } if (need_sense && !ap->ops->error_handler) ata_dump_status(ap->print_id, &qc->result_tf); qc->scsidone(cmd); ata_qc_free(qc); } /** * ata_scmd_need_defer - Check whether we need to defer scmd * @dev: ATA device to which the command is addressed * @is_io: Is the command IO (and thus possibly NCQ)? * * NCQ and non-NCQ commands cannot run together. As upper layer * only knows the queue depth, we are responsible for maintaining * exclusion. This function checks whether a new command can be * issued to @dev. * * LOCKING: * spin_lock_irqsave(host lock) * * RETURNS: * 1 if deferring is needed, 0 otherwise. */ static int ata_scmd_need_defer(struct ata_device *dev, int is_io) { struct ata_port *ap = dev->ap; int is_ncq = is_io && ata_ncq_enabled(dev); if (is_ncq) { if (!ata_tag_valid(ap->active_tag)) return 0; } else { if (!ata_tag_valid(ap->active_tag) && !ap->sactive) return 0; } return 1; } /** * ata_scsi_translate - Translate then issue SCSI command to ATA device * @dev: ATA device to which the command is addressed * @cmd: SCSI command to execute * @done: SCSI command completion function * @xlat_func: Actor which translates @cmd to an ATA taskfile * * Our ->queuecommand() function has decided that the SCSI * command issued can be directly translated into an ATA * command, rather than handled internally. * * This function sets up an ata_queued_cmd structure for the * SCSI command, and sends that ata_queued_cmd to the hardware. * * The xlat_func argument (actor) returns 0 if ready to execute * ATA command, else 1 to finish translation. If 1 is returned * then cmd->result (and possibly cmd->sense_buffer) are assumed * to be set reflecting an error condition or clean (early) * termination. * * LOCKING: * spin_lock_irqsave(host lock) * * RETURNS: * 0 on success, SCSI_ML_QUEUE_DEVICE_BUSY if the command * needs to be deferred. */ static int ata_scsi_translate(struct ata_device *dev, struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *), ata_xlat_func_t xlat_func) { struct ata_queued_cmd *qc; int is_io = xlat_func == ata_scsi_rw_xlat; VPRINTK("ENTER\n"); if (unlikely(ata_scmd_need_defer(dev, is_io))) goto defer; qc = ata_scsi_qc_new(dev, cmd, done); if (!qc) goto err_mem; /* data is present; dma-map it */ if (cmd->sc_data_direction == DMA_FROM_DEVICE || cmd->sc_data_direction == DMA_TO_DEVICE) { if (unlikely(cmd->request_bufflen < 1)) { ata_dev_printk(dev, KERN_WARNING, "WARNING: zero len r/w req\n"); goto err_did; } if (cmd->use_sg) ata_sg_init(qc, cmd->request_buffer, cmd->use_sg); else ata_sg_init_one(qc, cmd->request_buffer, cmd->request_bufflen); qc->dma_dir = cmd->sc_data_direction; } qc->complete_fn = ata_scsi_qc_complete; if (xlat_func(qc)) goto early_finish; /* select device, send command to hardware */ ata_qc_issue(qc); VPRINTK("EXIT\n"); return 0; early_finish: ata_qc_free(qc); done(cmd); DPRINTK("EXIT - early finish (good or error)\n"); return 0; err_did: ata_qc_free(qc); cmd->result = (DID_ERROR << 16); done(cmd); err_mem: DPRINTK("EXIT - internal\n"); return 0; defer: DPRINTK("EXIT - defer\n"); return SCSI_MLQUEUE_DEVICE_BUSY; } /** * ata_scsi_rbuf_get - Map response buffer. * @cmd: SCSI command containing buffer to be mapped. * @buf_out: Pointer to mapped area. * * Maps buffer contained within SCSI command @cmd. * * LOCKING: * spin_lock_irqsave(host lock) * * RETURNS: * Length of response buffer. */ static unsigned int ata_scsi_rbuf_get(struct scsi_cmnd *cmd, u8 **buf_out) { u8 *buf; unsigned int buflen; if (cmd->use_sg) { struct scatterlist *sg; sg = (struct scatterlist *) cmd->request_buffer; buf = kmap_atomic(sg->page, KM_IRQ0) + sg->offset; buflen = sg->length; } else { buf = cmd->request_buffer; buflen = cmd->request_bufflen; } *buf_out = buf; return buflen; } /** * ata_scsi_rbuf_put - Unmap response buffer. * @cmd: SCSI command containing buffer to be unmapped. * @buf: buffer to unmap * * Unmaps response buffer contained within @cmd. * * LOCKING: * spin_lock_irqsave(host lock) */ static inline void ata_scsi_rbuf_put(struct scsi_cmnd *cmd, u8 *buf) { if (cmd->use_sg) { struct scatterlist *sg; sg = (struct scatterlist *) cmd->request_buffer; kunmap_atomic(buf - sg->offset, KM_IRQ0); } } /** * ata_scsi_rbuf_fill - wrapper for SCSI command simulators * @args: device IDENTIFY data / SCSI command of interest. * @actor: Callback hook for desired SCSI command simulator * * Takes care of the hard work of simulating a SCSI command... * Mapping the response buffer, calling the command's handler, * and handling the handler's return value. This return value * indicates whether the handler wishes the SCSI command to be * completed successfully (0), or not (in which case cmd->result * and sense buffer are assumed to be set). * * LOCKING: * spin_lock_irqsave(host lock) */ void ata_scsi_rbuf_fill(struct ata_scsi_args *args, unsigned int (*actor) (struct ata_scsi_args *args, u8 *rbuf, unsigned int buflen)) { u8 *rbuf; unsigned int buflen, rc; struct scsi_cmnd *cmd = args->cmd; buflen = ata_scsi_rbuf_get(cmd, &rbuf); memset(rbuf, 0, buflen); rc = actor(args, rbuf, buflen); ata_scsi_rbuf_put(cmd, rbuf); if (rc == 0) cmd->result = SAM_STAT_GOOD; args->done(cmd); } /** * ATA_SCSI_RBUF_SET - helper to set values in SCSI response buffer * @idx: byte index into SCSI response buffer * @val: value to set * * To be used by SCSI command simulator functions. This macros * expects two local variables, u8 *rbuf and unsigned int buflen, * are in scope. * * LOCKING: * None. */ #define ATA_SCSI_RBUF_SET(idx, val) do { \ if ((idx) < buflen) rbuf[(idx)] = (u8)(val); \ } while (0) /** * ata_scsiop_inq_std - Simulate INQUIRY command * @args: device IDENTIFY data / SCSI command of interest. * @rbuf: Response buffer, to which simulated SCSI cmd output is sent. * @buflen: Response buffer length. * * Returns standard device identification data associated * with non-VPD INQUIRY command output. * * LOCKING: * spin_lock_irqsave(host lock) */ unsigned int ata_scsiop_inq_std(struct ata_scsi_args *args, u8 *rbuf, unsigned int buflen) { u8 hdr[] = { TYPE_DISK, 0, 0x5, /* claim SPC-3 version compatibility */ 2, 95 - 4 }; /* set scsi removeable (RMB) bit per ata bit */ if (ata_id_removeable(args->id)) hdr[1] |= (1 << 7); VPRINTK("ENTER\n"); memcpy(rbuf, hdr, sizeof(hdr)); if (buflen > 35) { memcpy(&rbuf[8], "ATA ", 8); ata_id_string(args->id, &rbuf[16], ATA_ID_PROD, 16); ata_id_string(args->id, &rbuf[32], ATA_ID_FW_REV, 4); if (rbuf[32] == 0 || rbuf[32] == ' ') memcpy(&rbuf[32], "n/a ", 4); } if (buflen > 63) { const u8 versions[] = { 0x60, /* SAM-3 (no version claimed) */ 0x03, 0x20, /* SBC-2 (no version claimed) */ 0x02, 0x60 /* SPC-3 (no version claimed) */ }; memcpy(rbuf + 59, versions, sizeof(versions)); } return 0; } /** * ata_scsiop_inq_00 - Simulate INQUIRY VPD page 0, list of pages * @args: device IDENTIFY data / SCSI command of interest. * @rbuf: Response buffer, to which simulated SCSI cmd output is sent. * @buflen: Response buffer length. * * Returns list of inquiry VPD pages available. * * LOCKING: * spin_lock_irqsave(host lock) */ unsigned int ata_scsiop_inq_00(struct ata_scsi_args *args, u8 *rbuf, unsigned int buflen) { const u8 pages[] = { 0x00, /* page 0x00, this page */ 0x80, /* page 0x80, unit serial no page */ 0x83 /* page 0x83, device ident page */ }; rbuf[3] = sizeof(pages); /* number of supported VPD pages */ if (buflen > 6) memcpy(rbuf + 4, pages, sizeof(pages)); return 0; } /** * ata_scsiop_inq_80 - Simulate INQUIRY VPD page 80, device serial number * @args: device IDENTIFY data / SCSI command of interest. * @rbuf: Response buffer, to which simulated SCSI cmd output is sent. * @buflen: Response buffer length. * * Returns ATA device serial number. * * LOCKING: * spin_lock_irqsave(host lock) */ unsigned int ata_scsiop_inq_80(struct ata_scsi_args *args, u8 *rbuf, unsigned int buflen) { const u8 hdr[] = { 0, 0x80, /* this page code */ 0, ATA_ID_SERNO_LEN, /* page len */ }; memcpy(rbuf, hdr, sizeof(hdr)); if (buflen > (ATA_ID_SERNO_LEN + 4 - 1)) ata_id_string(args->id, (unsigned char *) &rbuf[4], ATA_ID_SERNO, ATA_ID_SERNO_LEN); return 0; } /** * ata_scsiop_inq_83 - Simulate INQUIRY VPD page 83, device identity * @args: device IDENTIFY data / SCSI command of interest. * @rbuf: Response buffer, to which simulated SCSI cmd output is sent. * @buflen: Response buffer length. * * Yields two logical unit device identification designators: * - vendor specific ASCII containing the ATA serial number * - SAT defined "t10 vendor id based" containing ASCII vendor * name ("ATA "), model and serial numbers. * * LOCKING: * spin_lock_irqsave(host lock) */ unsigned int ata_scsiop_inq_83(struct ata_scsi_args *args, u8 *rbuf, unsigned int buflen) { int num; const int sat_model_serial_desc_len = 68; rbuf[1] = 0x83; /* this page code */ num = 4; if (buflen > (ATA_ID_SERNO_LEN + num + 3)) { /* piv=0, assoc=lu, code_set=ACSII, designator=vendor */ rbuf[num + 0] = 2; rbuf[num + 3] = ATA_ID_SERNO_LEN; num += 4; ata_id_string(args->id, (unsigned char *) rbuf + num, ATA_ID_SERNO, ATA_ID_SERNO_LEN); num += ATA_ID_SERNO_LEN; } if (buflen > (sat_model_serial_desc_len + num + 3)) { /* SAT defined lu model and serial numbers descriptor */ /* piv=0, assoc=lu, code_set=ACSII, designator=t10 vendor id */ rbuf[num + 0] = 2; rbuf[num + 1] = 1; rbuf[num + 3] = sat_model_serial_desc_len; num += 4; memcpy(rbuf + num, "ATA ", 8); num += 8; ata_id_string(args->id, (unsigned char *) rbuf + num, ATA_ID_PROD, ATA_ID_PROD_LEN); num += ATA_ID_PROD_LEN; ata_id_string(args->id, (unsigned char *) rbuf + num, ATA_ID_SERNO, ATA_ID_SERNO_LEN); num += ATA_ID_SERNO_LEN; } rbuf[3] = num - 4; /* page len (assume less than 256 bytes) */ return 0; } /** * ata_scsiop_noop - Command handler that simply returns success. * @args: device IDENTIFY data / SCSI command of interest. * @rbuf: Response buffer, to which simulated SCSI cmd output is sent. * @buflen: Response buffer length. * * No operation. Simply returns success to caller, to indicate * that the caller should successfully complete this SCSI command. * * LOCKING: * spin_lock_irqsave(host lock) */ unsigned int ata_scsiop_noop(struct ata_scsi_args *args, u8 *rbuf, unsigned int buflen) { VPRINTK("ENTER\n"); return 0; } /** * ata_msense_push - Push data onto MODE SENSE data output buffer * @ptr_io: (input/output) Location to store more output data * @last: End of output data buffer * @buf: Pointer to BLOB being added to output buffer * @buflen: Length of BLOB * * Store MODE SENSE data on an output buffer. * * LOCKING: * None. */ static void ata_msense_push(u8 **ptr_io, const u8 *last, const u8 *buf, unsigned int buflen) { u8 *ptr = *ptr_io; if ((ptr + buflen - 1) > last) return; memcpy(ptr, buf, buflen); ptr += buflen; *ptr_io = ptr; } /** * ata_msense_caching - Simulate MODE SENSE caching info page * @id: device IDENTIFY data * @ptr_io: (input/output) Location to store more output data * @last: End of output data buffer * * Generate a caching info page, which conditionally indicates * write caching to the SCSI layer, depending on device * capabilities. * * LOCKING: * None. */ static unsigned int ata_msense_caching(u16 *id, u8 **ptr_io, const u8 *last) { u8 page[CACHE_MPAGE_LEN]; memcpy(page, def_cache_mpage, sizeof(page)); if (ata_id_wcache_enabled(id)) page[2] |= (1 << 2); /* write cache enable */ if (!ata_id_rahead_enabled(id)) page[12] |= (1 << 5); /* disable read ahead */ ata_msense_push(ptr_io, last, page, sizeof(page)); return sizeof(page); } /** * ata_msense_ctl_mode - Simulate MODE SENSE control mode page * @dev: Device associated with this MODE SENSE command * @ptr_io: (input/output) Location to store more output data * @last: End of output data buffer * * Generate a generic MODE SENSE control mode page. * * LOCKING: * None. */ static unsigned int ata_msense_ctl_mode(u8 **ptr_io, const u8 *last) { ata_msense_push(ptr_io, last, def_control_mpage, sizeof(def_control_mpage)); return sizeof(def_control_mpage); } /** * ata_msense_rw_recovery - Simulate MODE SENSE r/w error recovery page * @dev: Device associated with this MODE SENSE command * @ptr_io: (input/output) Location to store more output data * @last: End of output data buffer * * Generate a generic MODE SENSE r/w error recovery page. * * LOCKING: * None. */ static unsigned int ata_msense_rw_recovery(u8 **ptr_io, const u8 *last) { ata_msense_push(ptr_io, last, def_rw_recovery_mpage, sizeof(def_rw_recovery_mpage)); return sizeof(def_rw_recovery_mpage); } /* * We can turn this into a real blacklist if it's needed, for now just * blacklist any Maxtor BANC1G10 revision firmware */ static int ata_dev_supports_fua(u16 *id) { unsigned char model[ATA_ID_PROD_LEN + 1], fw[ATA_ID_FW_REV_LEN + 1]; if (!libata_fua) return 0; if (!ata_id_has_fua(id)) return 0; ata_id_c_string(id, model, ATA_ID_PROD, sizeof(model)); ata_id_c_string(id, fw, ATA_ID_FW_REV, sizeof(fw)); if (strcmp(model, "Maxtor")) return 1; if (strcmp(fw, "BANC1G10")) return 1; return 0; /* blacklisted */ } /** * ata_scsiop_mode_sense - Simulate MODE SENSE 6, 10 commands * @args: device IDENTIFY data / SCSI command of interest. * @rbuf: Response buffer, to which simulated SCSI cmd output is sent. * @buflen: Response buffer length. * * Simulate MODE SENSE commands. Assume this is invoked for direct * access devices (e.g. disks) only. There should be no block * descriptor for other device types. * * LOCKING: * spin_lock_irqsave(host lock) */ unsigned int ata_scsiop_mode_sense(struct ata_scsi_args *args, u8 *rbuf, unsigned int buflen) { struct ata_device *dev = args->dev; u8 *scsicmd = args->cmd->cmnd, *p, *last; const u8 sat_blk_desc[] = { 0, 0, 0, 0, /* number of blocks: sat unspecified */ 0, 0, 0x2, 0x0 /* block length: 512 bytes */ }; u8 pg, spg; unsigned int ebd, page_control, six_byte, output_len, alloc_len, minlen; u8 dpofua; VPRINTK("ENTER\n"); six_byte = (scsicmd[0] == MODE_SENSE); ebd = !(scsicmd[1] & 0x8); /* dbd bit inverted == edb */ /* * LLBA bit in msense(10) ignored (compliant) */ page_control = scsicmd[2] >> 6; switch (page_control) { case 0: /* current */ break; /* supported */ case 3: /* saved */ goto saving_not_supp; case 1: /* changeable */ case 2: /* defaults */ default: goto invalid_fld; } if (six_byte) { output_len = 4 + (ebd ? 8 : 0); alloc_len = scsicmd[4]; } else { output_len = 8 + (ebd ? 8 : 0); alloc_len = (scsicmd[7] << 8) + scsicmd[8]; } minlen = (alloc_len < buflen) ? alloc_len : buflen; p = rbuf + output_len; last = rbuf + minlen - 1; pg = scsicmd[2] & 0x3f; spg = scsicmd[3]; /* * No mode subpages supported (yet) but asking for _all_ * subpages may be valid */ if (spg && (spg != ALL_SUB_MPAGES)) goto invalid_fld; switch(pg) { case RW_RECOVERY_MPAGE: output_len += ata_msense_rw_recovery(&p, last); break; case CACHE_MPAGE: output_len += ata_msense_caching(args->id, &p, last); break; case CONTROL_MPAGE: { output_len += ata_msense_ctl_mode(&p, last); break; } case ALL_MPAGES: output_len += ata_msense_rw_recovery(&p, last); output_len += ata_msense_caching(args->id, &p, last); output_len += ata_msense_ctl_mode(&p, last); break; default: /* invalid page code */ goto invalid_fld; } if (minlen < 1) return 0; dpofua = 0; if (ata_dev_supports_fua(args->id) && (dev->flags & ATA_DFLAG_LBA48) && (!(dev->flags & ATA_DFLAG_PIO) || dev->multi_count)) dpofua = 1 << 4; if (six_byte) { output_len--; rbuf[0] = output_len; if (minlen > 2) rbuf[2] |= dpofua; if (ebd) { if (minlen > 3) rbuf[3] = sizeof(sat_blk_desc); if (minlen > 11) memcpy(rbuf + 4, sat_blk_desc, sizeof(sat_blk_desc)); } } else { output_len -= 2; rbuf[0] = output_len >> 8; if (minlen > 1) rbuf[1] = output_len; if (minlen > 3) rbuf[3] |= dpofua; if (ebd) { if (minlen > 7) rbuf[7] = sizeof(sat_blk_desc); if (minlen > 15) memcpy(rbuf + 8, sat_blk_desc, sizeof(sat_blk_desc)); } } return 0; invalid_fld: ata_scsi_set_sense(args->cmd, ILLEGAL_REQUEST, 0x24, 0x0); /* "Invalid field in cbd" */ return 1; saving_not_supp: ata_scsi_set_sense(args->cmd, ILLEGAL_REQUEST, 0x39, 0x0); /* "Saving parameters not supported" */ return 1; } /** * ata_scsiop_read_cap - Simulate READ CAPACITY[ 16] commands * @args: device IDENTIFY data / SCSI command of interest. * @rbuf: Response buffer, to which simulated SCSI cmd output is sent. * @buflen: Response buffer length. * * Simulate READ CAPACITY commands. * * LOCKING: * None. */ unsigned int ata_scsiop_read_cap(struct ata_scsi_args *args, u8 *rbuf, unsigned int buflen) { u64 last_lba = args->dev->n_sectors - 1; /* LBA of the last block */ VPRINTK("ENTER\n"); if (args->cmd->cmnd[0] == READ_CAPACITY) { if (last_lba >= 0xffffffffULL) last_lba = 0xffffffff; /* sector count, 32-bit */ ATA_SCSI_RBUF_SET(0, last_lba >> (8 * 3)); ATA_SCSI_RBUF_SET(1, last_lba >> (8 * 2)); ATA_SCSI_RBUF_SET(2, last_lba >> (8 * 1)); ATA_SCSI_RBUF_SET(3, last_lba); /* sector size */ ATA_SCSI_RBUF_SET(6, ATA_SECT_SIZE >> 8); ATA_SCSI_RBUF_SET(7, ATA_SECT_SIZE); } else { /* sector count, 64-bit */ ATA_SCSI_RBUF_SET(0, last_lba >> (8 * 7)); ATA_SCSI_RBUF_SET(1, last_lba >> (8 * 6)); ATA_SCSI_RBUF_SET(2, last_lba >> (8 * 5)); ATA_SCSI_RBUF_SET(3, last_lba >> (8 * 4)); ATA_SCSI_RBUF_SET(4, last_lba >> (8 * 3)); ATA_SCSI_RBUF_SET(5, last_lba >> (8 * 2)); ATA_SCSI_RBUF_SET(6, last_lba >> (8 * 1)); ATA_SCSI_RBUF_SET(7, last_lba); /* sector size */ ATA_SCSI_RBUF_SET(10, ATA_SECT_SIZE >> 8); ATA_SCSI_RBUF_SET(11, ATA_SECT_SIZE); } return 0; } /** * ata_scsiop_report_luns - Simulate REPORT LUNS command * @args: device IDENTIFY data / SCSI command of interest. * @rbuf: Response buffer, to which simulated SCSI cmd output is sent. * @buflen: Response buffer length. * * Simulate REPORT LUNS command. * * LOCKING: * spin_lock_irqsave(host lock) */ unsigned int ata_scsiop_report_luns(struct ata_scsi_args *args, u8 *rbuf, unsigned int buflen) { VPRINTK("ENTER\n"); rbuf[3] = 8; /* just one lun, LUN 0, size 8 bytes */ return 0; } /** * ata_scsi_set_sense - Set SCSI sense data and status * @cmd: SCSI request to be handled * @sk: SCSI-defined sense key * @asc: SCSI-defined additional sense code * @ascq: SCSI-defined additional sense code qualifier * * Helper function that builds a valid fixed format, current * response code and the given sense key (sk), additional sense * code (asc) and additional sense code qualifier (ascq) with * a SCSI command status of %SAM_STAT_CHECK_CONDITION and * DRIVER_SENSE set in the upper bits of scsi_cmnd::result . * * LOCKING: * Not required */ void ata_scsi_set_sense(struct scsi_cmnd *cmd, u8 sk, u8 asc, u8 ascq) { cmd->result = (DRIVER_SENSE << 24) | SAM_STAT_CHECK_CONDITION; cmd->sense_buffer[0] = 0x70; /* fixed format, current */ cmd->sense_buffer[2] = sk; cmd->sense_buffer[7] = 18 - 8; /* additional sense length */ cmd->sense_buffer[12] = asc; cmd->sense_buffer[13] = ascq; } /** * ata_scsi_badcmd - End a SCSI request with an error * @cmd: SCSI request to be handled * @done: SCSI command completion function * @asc: SCSI-defined additional sense code * @ascq: SCSI-defined additional sense code qualifier * * Helper function that completes a SCSI command with * %SAM_STAT_CHECK_CONDITION, with a sense key %ILLEGAL_REQUEST * and the specified additional sense codes. * * LOCKING: * spin_lock_irqsave(host lock) */ void ata_scsi_badcmd(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *), u8 asc, u8 ascq) { DPRINTK("ENTER\n"); ata_scsi_set_sense(cmd, ILLEGAL_REQUEST, asc, ascq); done(cmd); } static void atapi_sense_complete(struct ata_queued_cmd *qc) { if (qc->err_mask && ((qc->err_mask & AC_ERR_DEV) == 0)) { /* FIXME: not quite right; we don't want the * translation of taskfile registers into * a sense descriptors, since that's only * correct for ATA, not ATAPI */ ata_gen_passthru_sense(qc); } qc->scsidone(qc->scsicmd); ata_qc_free(qc); } /* is it pointless to prefer PIO for "safety reasons"? */ static inline int ata_pio_use_silly(struct ata_port *ap) { return (ap->flags & ATA_FLAG_PIO_DMA); } static void atapi_request_sense(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct scsi_cmnd *cmd = qc->scsicmd; DPRINTK("ATAPI request sense\n"); /* FIXME: is this needed? */ memset(cmd->sense_buffer, 0, sizeof(cmd->sense_buffer)); ap->ops->tf_read(ap, &qc->tf); /* fill these in, for the case where they are -not- overwritten */ cmd->sense_buffer[0] = 0x70; cmd->sense_buffer[2] = qc->tf.feature >> 4; ata_qc_reinit(qc); ata_sg_init_one(qc, cmd->sense_buffer, sizeof(cmd->sense_buffer)); qc->dma_dir = DMA_FROM_DEVICE; memset(&qc->cdb, 0, qc->dev->cdb_len); qc->cdb[0] = REQUEST_SENSE; qc->cdb[4] = SCSI_SENSE_BUFFERSIZE; qc->tf.flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE; qc->tf.command = ATA_CMD_PACKET; if (ata_pio_use_silly(ap)) { qc->tf.protocol = ATA_PROT_ATAPI_DMA; qc->tf.feature |= ATAPI_PKT_DMA; } else { qc->tf.protocol = ATA_PROT_ATAPI; qc->tf.lbam = (8 * 1024) & 0xff; qc->tf.lbah = (8 * 1024) >> 8; } qc->nbytes = SCSI_SENSE_BUFFERSIZE; qc->complete_fn = atapi_sense_complete; ata_qc_issue(qc); DPRINTK("EXIT\n"); } static void atapi_qc_complete(struct ata_queued_cmd *qc) { struct scsi_cmnd *cmd = qc->scsicmd; unsigned int err_mask = qc->err_mask; VPRINTK("ENTER, err_mask 0x%X\n", err_mask); /* handle completion from new EH */ if (unlikely(qc->ap->ops->error_handler && (err_mask || qc->flags & ATA_QCFLAG_SENSE_VALID))) { if (!(qc->flags & ATA_QCFLAG_SENSE_VALID)) { /* FIXME: not quite right; we don't want the * translation of taskfile registers into a * sense descriptors, since that's only * correct for ATA, not ATAPI */ ata_gen_passthru_sense(qc); } /* SCSI EH automatically locks door if sdev->locked is * set. Sometimes door lock request continues to * fail, for example, when no media is present. This * creates a loop - SCSI EH issues door lock which * fails and gets invoked again to acquire sense data * for the failed command. * * If door lock fails, always clear sdev->locked to * avoid this infinite loop. */ if (qc->cdb[0] == ALLOW_MEDIUM_REMOVAL) qc->dev->sdev->locked = 0; qc->scsicmd->result = SAM_STAT_CHECK_CONDITION; qc->scsidone(cmd); ata_qc_free(qc); return; } /* successful completion or old EH failure path */ if (unlikely(err_mask & AC_ERR_DEV)) { cmd->result = SAM_STAT_CHECK_CONDITION; atapi_request_sense(qc); return; } else if (unlikely(err_mask)) { /* FIXME: not quite right; we don't want the * translation of taskfile registers into * a sense descriptors, since that's only * correct for ATA, not ATAPI */ ata_gen_passthru_sense(qc); } else { u8 *scsicmd = cmd->cmnd; if ((scsicmd[0] == INQUIRY) && ((scsicmd[1] & 0x03) == 0)) { u8 *buf = NULL; unsigned int buflen; buflen = ata_scsi_rbuf_get(cmd, &buf); /* ATAPI devices typically report zero for their SCSI version, * and sometimes deviate from the spec WRT response data * format. If SCSI version is reported as zero like normal, * then we make the following fixups: 1) Fake MMC-5 version, * to indicate to the Linux scsi midlayer this is a modern * device. 2) Ensure response data format / ATAPI information * are always correct. */ if (buf[2] == 0) { buf[2] = 0x5; buf[3] = 0x32; } ata_scsi_rbuf_put(cmd, buf); } cmd->result = SAM_STAT_GOOD; } qc->scsidone(cmd); ata_qc_free(qc); } /** * atapi_xlat - Initialize PACKET taskfile * @qc: command structure to be initialized * * LOCKING: * spin_lock_irqsave(host lock) * * RETURNS: * Zero on success, non-zero on failure. */ static unsigned int atapi_xlat(struct ata_queued_cmd *qc) { struct scsi_cmnd *scmd = qc->scsicmd; struct ata_device *dev = qc->dev; int using_pio = (dev->flags & ATA_DFLAG_PIO); int nodata = (scmd->sc_data_direction == DMA_NONE); if (!using_pio) /* Check whether ATAPI DMA is safe */ if (ata_check_atapi_dma(qc)) using_pio = 1; memset(qc->cdb, 0, dev->cdb_len); memcpy(qc->cdb, scmd->cmnd, scmd->cmd_len); qc->complete_fn = atapi_qc_complete; qc->tf.flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE; if (scmd->sc_data_direction == DMA_TO_DEVICE) { qc->tf.flags |= ATA_TFLAG_WRITE; DPRINTK("direction: write\n"); } qc->tf.command = ATA_CMD_PACKET; /* no data, or PIO data xfer */ if (using_pio || nodata) { if (nodata) qc->tf.protocol = ATA_PROT_ATAPI_NODATA; else qc->tf.protocol = ATA_PROT_ATAPI; qc->tf.lbam = (8 * 1024) & 0xff; qc->tf.lbah = (8 * 1024) >> 8; } /* DMA data xfer */ else { qc->tf.protocol = ATA_PROT_ATAPI_DMA; qc->tf.feature |= ATAPI_PKT_DMA; if (atapi_dmadir && (scmd->sc_data_direction != DMA_TO_DEVICE)) /* some SATA bridges need us to indicate data xfer direction */ qc->tf.feature |= ATAPI_DMADIR; } qc->nbytes = scmd->request_bufflen; return 0; } static struct ata_device * ata_find_dev(struct ata_port *ap, int id) { if (likely(id < ATA_MAX_DEVICES)) return &ap->device[id]; return NULL; } static struct ata_device * __ata_scsi_find_dev(struct ata_port *ap, const struct scsi_device *scsidev) { /* skip commands not addressed to targets we simulate */ if (unlikely(scsidev->channel || scsidev->lun)) return NULL; return ata_find_dev(ap, scsidev->id); } /** * ata_scsi_dev_enabled - determine if device is enabled * @dev: ATA device * * Determine if commands should be sent to the specified device. * * LOCKING: * spin_lock_irqsave(host lock) * * RETURNS: * 0 if commands are not allowed / 1 if commands are allowed */ static int ata_scsi_dev_enabled(struct ata_device *dev) { if (unlikely(!ata_dev_enabled(dev))) return 0; if (!atapi_enabled || (dev->ap->flags & ATA_FLAG_NO_ATAPI)) { if (unlikely(dev->class == ATA_DEV_ATAPI)) { ata_dev_printk(dev, KERN_WARNING, "WARNING: ATAPI is %s, device ignored.\n", atapi_enabled ? "not supported with this driver" : "disabled"); return 0; } } return 1; } /** * ata_scsi_find_dev - lookup ata_device from scsi_cmnd * @ap: ATA port to which the device is attached * @scsidev: SCSI device from which we derive the ATA device * * Given various information provided in struct scsi_cmnd, * map that onto an ATA bus, and using that mapping * determine which ata_device is associated with the * SCSI command to be sent. * * LOCKING: * spin_lock_irqsave(host lock) * * RETURNS: * Associated ATA device, or %NULL if not found. */ static struct ata_device * ata_scsi_find_dev(struct ata_port *ap, const struct scsi_device *scsidev) { struct ata_device *dev = __ata_scsi_find_dev(ap, scsidev); if (unlikely(!dev || !ata_scsi_dev_enabled(dev))) return NULL; return dev; } /* * ata_scsi_map_proto - Map pass-thru protocol value to taskfile value. * @byte1: Byte 1 from pass-thru CDB. * * RETURNS: * ATA_PROT_UNKNOWN if mapping failed/unimplemented, protocol otherwise. */ static u8 ata_scsi_map_proto(u8 byte1) { switch((byte1 & 0x1e) >> 1) { case 3: /* Non-data */ return ATA_PROT_NODATA; case 6: /* DMA */ return ATA_PROT_DMA; case 4: /* PIO Data-in */ case 5: /* PIO Data-out */ return ATA_PROT_PIO; case 10: /* Device Reset */ case 0: /* Hard Reset */ case 1: /* SRST */ case 2: /* Bus Idle */ case 7: /* Packet */ case 8: /* DMA Queued */ case 9: /* Device Diagnostic */ case 11: /* UDMA Data-in */ case 12: /* UDMA Data-Out */ case 13: /* FPDMA */ default: /* Reserved */ break; } return ATA_PROT_UNKNOWN; } /** * ata_scsi_pass_thru - convert ATA pass-thru CDB to taskfile * @qc: command structure to be initialized * * Handles either 12 or 16-byte versions of the CDB. * * RETURNS: * Zero on success, non-zero on failure. */ static unsigned int ata_scsi_pass_thru(struct ata_queued_cmd *qc) { struct ata_taskfile *tf = &(qc->tf); struct scsi_cmnd *scmd = qc->scsicmd; struct ata_device *dev = qc->dev; const u8 *cdb = scmd->cmnd; if ((tf->protocol = ata_scsi_map_proto(cdb[1])) == ATA_PROT_UNKNOWN) goto invalid_fld; /* We may not issue DMA commands if no DMA mode is set */ if (tf->protocol == ATA_PROT_DMA && dev->dma_mode == 0) goto invalid_fld; if (cdb[1] & 0xe0) /* PIO multi not supported yet */ goto invalid_fld; /* * 12 and 16 byte CDBs use different offsets to * provide the various register values. */ if (cdb[0] == ATA_16) { /* * 16-byte CDB - may contain extended commands. * * If that is the case, copy the upper byte register values. */ if (cdb[1] & 0x01) { tf->hob_feature = cdb[3]; tf->hob_nsect = cdb[5]; tf->hob_lbal = cdb[7]; tf->hob_lbam = cdb[9]; tf->hob_lbah = cdb[11]; tf->flags |= ATA_TFLAG_LBA48; } else tf->flags &= ~ATA_TFLAG_LBA48; /* * Always copy low byte, device and command registers. */ tf->feature = cdb[4]; tf->nsect = cdb[6]; tf->lbal = cdb[8]; tf->lbam = cdb[10]; tf->lbah = cdb[12]; tf->device = cdb[13]; tf->command = cdb[14]; } else { /* * 12-byte CDB - incapable of extended commands. */ tf->flags &= ~ATA_TFLAG_LBA48; tf->feature = cdb[3]; tf->nsect = cdb[4]; tf->lbal = cdb[5]; tf->lbam = cdb[6]; tf->lbah = cdb[7]; tf->device = cdb[8]; tf->command = cdb[9]; } /* * If slave is possible, enforce correct master/slave bit */ if (qc->ap->flags & ATA_FLAG_SLAVE_POSS) tf->device = qc->dev->devno ? tf->device | ATA_DEV1 : tf->device & ~ATA_DEV1; /* READ/WRITE LONG use a non-standard sect_size */ qc->sect_size = ATA_SECT_SIZE; switch (tf->command) { case ATA_CMD_READ_LONG: case ATA_CMD_READ_LONG_ONCE: case ATA_CMD_WRITE_LONG: case ATA_CMD_WRITE_LONG_ONCE: if (tf->protocol != ATA_PROT_PIO || tf->nsect != 1) goto invalid_fld; qc->sect_size = scmd->request_bufflen; } /* * Filter SET_FEATURES - XFER MODE command -- otherwise, * SET_FEATURES - XFER MODE must be preceded/succeeded * by an update to hardware-specific registers for each * controller (i.e. the reason for ->set_piomode(), * ->set_dmamode(), and ->post_set_mode() hooks). */ if ((tf->command == ATA_CMD_SET_FEATURES) && (tf->feature == SETFEATURES_XFER)) goto invalid_fld; /* * Set flags so that all registers will be written, * and pass on write indication (used for PIO/DMA * setup.) */ tf->flags |= (ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE); if (scmd->sc_data_direction == DMA_TO_DEVICE) tf->flags |= ATA_TFLAG_WRITE; /* * Set transfer length. * * TODO: find out if we need to do more here to * cover scatter/gather case. */ qc->nbytes = scmd->request_bufflen; /* request result TF */ qc->flags |= ATA_QCFLAG_RESULT_TF; return 0; invalid_fld: ata_scsi_set_sense(scmd, ILLEGAL_REQUEST, 0x24, 0x00); /* "Invalid field in cdb" */ return 1; } /** * ata_get_xlat_func - check if SCSI to ATA translation is possible * @dev: ATA device * @cmd: SCSI command opcode to consider * * Look up the SCSI command given, and determine whether the * SCSI command is to be translated or simulated. * * RETURNS: * Pointer to translation function if possible, %NULL if not. */ static inline ata_xlat_func_t ata_get_xlat_func(struct ata_device *dev, u8 cmd) { switch (cmd) { case READ_6: case READ_10: case READ_16: case WRITE_6: case WRITE_10: case WRITE_16: return ata_scsi_rw_xlat; case SYNCHRONIZE_CACHE: if (ata_try_flush_cache(dev)) return ata_scsi_flush_xlat; break; case VERIFY: case VERIFY_16: return ata_scsi_verify_xlat; case ATA_12: case ATA_16: return ata_scsi_pass_thru; case START_STOP: return ata_scsi_start_stop_xlat; } return NULL; } /** * ata_scsi_dump_cdb - dump SCSI command contents to dmesg * @ap: ATA port to which the command was being sent * @cmd: SCSI command to dump * * Prints the contents of a SCSI command via printk(). */ static inline void ata_scsi_dump_cdb(struct ata_port *ap, struct scsi_cmnd *cmd) { #ifdef ATA_DEBUG struct scsi_device *scsidev = cmd->device; u8 *scsicmd = cmd->cmnd; DPRINTK("CDB (%u:%d,%d,%d) %02x %02x %02x %02x %02x %02x %02x %02x %02x\n", ap->print_id, scsidev->channel, scsidev->id, scsidev->lun, scsicmd[0], scsicmd[1], scsicmd[2], scsicmd[3], scsicmd[4], scsicmd[5], scsicmd[6], scsicmd[7], scsicmd[8]); #endif } static inline int __ata_scsi_queuecmd(struct scsi_cmnd *scmd, void (*done)(struct scsi_cmnd *), struct ata_device *dev) { int rc = 0; if (unlikely(!scmd->cmd_len || scmd->cmd_len > dev->cdb_len)) { DPRINTK("bad CDB len=%u, max=%u\n", scmd->cmd_len, dev->cdb_len); scmd->result = DID_ERROR << 16; done(scmd); return 0; } if (dev->class == ATA_DEV_ATA) { ata_xlat_func_t xlat_func = ata_get_xlat_func(dev, scmd->cmnd[0]); if (xlat_func) rc = ata_scsi_translate(dev, scmd, done, xlat_func); else ata_scsi_simulate(dev, scmd, done); } else rc = ata_scsi_translate(dev, scmd, done, atapi_xlat); return rc; } /** * ata_scsi_queuecmd - Issue SCSI cdb to libata-managed device * @cmd: SCSI command to be sent * @done: Completion function, called when command is complete * * In some cases, this function translates SCSI commands into * ATA taskfiles, and queues the taskfiles to be sent to * hardware. In other cases, this function simulates a * SCSI device by evaluating and responding to certain * SCSI commands. This creates the overall effect of * ATA and ATAPI devices appearing as SCSI devices. * * LOCKING: * Releases scsi-layer-held lock, and obtains host lock. * * RETURNS: * Return value from __ata_scsi_queuecmd() if @cmd can be queued, * 0 otherwise. */ int ata_scsi_queuecmd(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *)) { struct ata_port *ap; struct ata_device *dev; struct scsi_device *scsidev = cmd->device; struct Scsi_Host *shost = scsidev->host; int rc = 0; ap = ata_shost_to_port(shost); spin_unlock(shost->host_lock); spin_lock(ap->lock); ata_scsi_dump_cdb(ap, cmd); dev = ata_scsi_find_dev(ap, scsidev); if (likely(dev)) rc = __ata_scsi_queuecmd(cmd, done, dev); else { cmd->result = (DID_BAD_TARGET << 16); done(cmd); } spin_unlock(ap->lock); spin_lock(shost->host_lock); return rc; } /** * ata_scsi_simulate - simulate SCSI command on ATA device * @dev: the target device * @cmd: SCSI command being sent to device. * @done: SCSI command completion function. * * Interprets and directly executes a select list of SCSI commands * that can be handled internally. * * LOCKING: * spin_lock_irqsave(host lock) */ void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *)) { struct ata_scsi_args args; const u8 *scsicmd = cmd->cmnd; args.dev = dev; args.id = dev->id; args.cmd = cmd; args.done = done; switch(scsicmd[0]) { /* no-op's, complete with success */ case SYNCHRONIZE_CACHE: case REZERO_UNIT: case SEEK_6: case SEEK_10: case TEST_UNIT_READY: case FORMAT_UNIT: /* FIXME: correct? */ case SEND_DIAGNOSTIC: /* FIXME: correct? */ ata_scsi_rbuf_fill(&args, ata_scsiop_noop); break; case INQUIRY: if (scsicmd[1] & 2) /* is CmdDt set? */ ata_scsi_invalid_field(cmd, done); else if ((scsicmd[1] & 1) == 0) /* is EVPD clear? */ ata_scsi_rbuf_fill(&args, ata_scsiop_inq_std); else if (scsicmd[2] == 0x00) ata_scsi_rbuf_fill(&args, ata_scsiop_inq_00); else if (scsicmd[2] == 0x80) ata_scsi_rbuf_fill(&args, ata_scsiop_inq_80); else if (scsicmd[2] == 0x83) ata_scsi_rbuf_fill(&args, ata_scsiop_inq_83); else ata_scsi_invalid_field(cmd, done); break; case MODE_SENSE: case MODE_SENSE_10: ata_scsi_rbuf_fill(&args, ata_scsiop_mode_sense); break; case MODE_SELECT: /* unconditionally return */ case MODE_SELECT_10: /* bad-field-in-cdb */ ata_scsi_invalid_field(cmd, done); break; case READ_CAPACITY: ata_scsi_rbuf_fill(&args, ata_scsiop_read_cap); break; case SERVICE_ACTION_IN: if ((scsicmd[1] & 0x1f) == SAI_READ_CAPACITY_16) ata_scsi_rbuf_fill(&args, ata_scsiop_read_cap); else ata_scsi_invalid_field(cmd, done); break; case REPORT_LUNS: ata_scsi_rbuf_fill(&args, ata_scsiop_report_luns); break; /* mandatory commands we haven't implemented yet */ case REQUEST_SENSE: /* all other commands */ default: ata_scsi_set_sense(cmd, ILLEGAL_REQUEST, 0x20, 0x0); /* "Invalid command operation code" */ done(cmd); break; } } int ata_scsi_add_hosts(struct ata_host *host, struct scsi_host_template *sht) { int i, rc; for (i = 0; i < host->n_ports; i++) { struct ata_port *ap = host->ports[i]; struct Scsi_Host *shost; rc = -ENOMEM; shost = scsi_host_alloc(sht, sizeof(struct ata_port *)); if (!shost) goto err_alloc; *(struct ata_port **)&shost->hostdata[0] = ap; ap->scsi_host = shost; shost->transportt = &ata_scsi_transport_template; shost->unique_id = ap->print_id; shost->max_id = 16; shost->max_lun = 1; shost->max_channel = 1; shost->max_cmd_len = 16; rc = scsi_add_host(ap->scsi_host, ap->host->dev); if (rc) goto err_add; } return 0; err_add: scsi_host_put(host->ports[i]->scsi_host); err_alloc: while (--i >= 0) { struct Scsi_Host *shost = host->ports[i]->scsi_host; scsi_remove_host(shost); scsi_host_put(shost); } return rc; } void ata_scsi_scan_host(struct ata_port *ap) { unsigned int i; if (ap->flags & ATA_FLAG_DISABLED) return; for (i = 0; i < ATA_MAX_DEVICES; i++) { struct ata_device *dev = &ap->device[i]; struct scsi_device *sdev; if (!ata_dev_enabled(dev) || dev->sdev) continue; sdev = __scsi_add_device(ap->scsi_host, 0, i, 0, NULL); if (!IS_ERR(sdev)) { dev->sdev = sdev; scsi_device_put(sdev); } } } /** * ata_scsi_offline_dev - offline attached SCSI device * @dev: ATA device to offline attached SCSI device for * * This function is called from ata_eh_hotplug() and responsible * for taking the SCSI device attached to @dev offline. This * function is called with host lock which protects dev->sdev * against clearing. * * LOCKING: * spin_lock_irqsave(host lock) * * RETURNS: * 1 if attached SCSI device exists, 0 otherwise. */ int ata_scsi_offline_dev(struct ata_device *dev) { if (dev->sdev) { scsi_device_set_state(dev->sdev, SDEV_OFFLINE); return 1; } return 0; } /** * ata_scsi_remove_dev - remove attached SCSI device * @dev: ATA device to remove attached SCSI device for * * This function is called from ata_eh_scsi_hotplug() and * responsible for removing the SCSI device attached to @dev. * * LOCKING: * Kernel thread context (may sleep). */ static void ata_scsi_remove_dev(struct ata_device *dev) { struct ata_port *ap = dev->ap; struct scsi_device *sdev; unsigned long flags; /* Alas, we need to grab scan_mutex to ensure SCSI device * state doesn't change underneath us and thus * scsi_device_get() always succeeds. The mutex locking can * be removed if there is __scsi_device_get() interface which * increments reference counts regardless of device state. */ mutex_lock(&ap->scsi_host->scan_mutex); spin_lock_irqsave(ap->lock, flags); /* clearing dev->sdev is protected by host lock */ sdev = dev->sdev; dev->sdev = NULL; if (sdev) { /* If user initiated unplug races with us, sdev can go * away underneath us after the host lock and * scan_mutex are released. Hold onto it. */ if (scsi_device_get(sdev) == 0) { /* The following ensures the attached sdev is * offline on return from ata_scsi_offline_dev() * regardless it wins or loses the race * against this function. */ scsi_device_set_state(sdev, SDEV_OFFLINE); } else { WARN_ON(1); sdev = NULL; } } spin_unlock_irqrestore(ap->lock, flags); mutex_unlock(&ap->scsi_host->scan_mutex); if (sdev) { ata_dev_printk(dev, KERN_INFO, "detaching (SCSI %s)\n", sdev->sdev_gendev.bus_id); scsi_remove_device(sdev); scsi_device_put(sdev); } } /** * ata_scsi_hotplug - SCSI part of hotplug * @work: Pointer to ATA port to perform SCSI hotplug on * * Perform SCSI part of hotplug. It's executed from a separate * workqueue after EH completes. This is necessary because SCSI * hot plugging requires working EH and hot unplugging is * synchronized with hot plugging with a mutex. * * LOCKING: * Kernel thread context (may sleep). */ void ata_scsi_hotplug(struct work_struct *work) { struct ata_port *ap = container_of(work, struct ata_port, hotplug_task.work); int i; if (ap->pflags & ATA_PFLAG_UNLOADING) { DPRINTK("ENTER/EXIT - unloading\n"); return; } DPRINTK("ENTER\n"); /* unplug detached devices */ for (i = 0; i < ATA_MAX_DEVICES; i++) { struct ata_device *dev = &ap->device[i]; unsigned long flags; if (!(dev->flags & ATA_DFLAG_DETACHED)) continue; spin_lock_irqsave(ap->lock, flags); dev->flags &= ~ATA_DFLAG_DETACHED; spin_unlock_irqrestore(ap->lock, flags); ata_scsi_remove_dev(dev); } /* scan for new ones */ ata_scsi_scan_host(ap); /* If we scanned while EH was in progress, scan would have * failed silently. Requeue if there are enabled but * unattached devices. */ for (i = 0; i < ATA_MAX_DEVICES; i++) { struct ata_device *dev = &ap->device[i]; if (ata_dev_enabled(dev) && !dev->sdev) { queue_delayed_work(ata_aux_wq, &ap->hotplug_task, round_jiffies_relative(HZ)); break; } } DPRINTK("EXIT\n"); } /** * ata_scsi_user_scan - indication for user-initiated bus scan * @shost: SCSI host to scan * @channel: Channel to scan * @id: ID to scan * @lun: LUN to scan * * This function is called when user explicitly requests bus * scan. Set probe pending flag and invoke EH. * * LOCKING: * SCSI layer (we don't care) * * RETURNS: * Zero. */ static int ata_scsi_user_scan(struct Scsi_Host *shost, unsigned int channel, unsigned int id, unsigned int lun) { struct ata_port *ap = ata_shost_to_port(shost); unsigned long flags; int rc = 0; if (!ap->ops->error_handler) return -EOPNOTSUPP; if ((channel != SCAN_WILD_CARD && channel != 0) || (lun != SCAN_WILD_CARD && lun != 0)) return -EINVAL; spin_lock_irqsave(ap->lock, flags); if (id == SCAN_WILD_CARD) { ap->eh_info.probe_mask |= (1 << ATA_MAX_DEVICES) - 1; ap->eh_info.action |= ATA_EH_SOFTRESET; } else { struct ata_device *dev = ata_find_dev(ap, id); if (dev) { ap->eh_info.probe_mask |= 1 << dev->devno; ap->eh_info.action |= ATA_EH_SOFTRESET; ap->eh_info.flags |= ATA_EHI_RESUME_LINK; } else rc = -EINVAL; } if (rc == 0) { ata_port_schedule_eh(ap); spin_unlock_irqrestore(ap->lock, flags); ata_port_wait_eh(ap); } else spin_unlock_irqrestore(ap->lock, flags); return rc; } /** * ata_scsi_dev_rescan - initiate scsi_rescan_device() * @work: Pointer to ATA port to perform scsi_rescan_device() * * After ATA pass thru (SAT) commands are executed successfully, * libata need to propagate the changes to SCSI layer. This * function must be executed from ata_aux_wq such that sdev * attach/detach don't race with rescan. * * LOCKING: * Kernel thread context (may sleep). */ void ata_scsi_dev_rescan(struct work_struct *work) { struct ata_port *ap = container_of(work, struct ata_port, scsi_rescan_task); unsigned long flags; unsigned int i; spin_lock_irqsave(ap->lock, flags); for (i = 0; i < ATA_MAX_DEVICES; i++) { struct ata_device *dev = &ap->device[i]; struct scsi_device *sdev = dev->sdev; if (!ata_dev_enabled(dev) || !sdev) continue; if (scsi_device_get(sdev)) continue; spin_unlock_irqrestore(ap->lock, flags); scsi_rescan_device(&(sdev->sdev_gendev)); scsi_device_put(sdev); spin_lock_irqsave(ap->lock, flags); } spin_unlock_irqrestore(ap->lock, flags); } /** * ata_sas_port_alloc - Allocate port for a SAS attached SATA device * @host: ATA host container for all SAS ports * @port_info: Information from low-level host driver * @shost: SCSI host that the scsi device is attached to * * LOCKING: * PCI/etc. bus probe sem. * * RETURNS: * ata_port pointer on success / NULL on failure. */ struct ata_port *ata_sas_port_alloc(struct ata_host *host, struct ata_port_info *port_info, struct Scsi_Host *shost) { struct ata_port *ap; ap = ata_port_alloc(host); if (!ap) return NULL; ap->port_no = 0; ap->lock = shost->host_lock; ap->pio_mask = port_info->pio_mask; ap->mwdma_mask = port_info->mwdma_mask; ap->udma_mask = port_info->udma_mask; ap->flags |= port_info->flags; ap->ops = port_info->port_ops; ap->cbl = ATA_CBL_SATA; return ap; } EXPORT_SYMBOL_GPL(ata_sas_port_alloc); /** * ata_sas_port_start - Set port up for dma. * @ap: Port to initialize * * Called just after data structures for each port are * initialized. Allocates DMA pad. * * May be used as the port_start() entry in ata_port_operations. * * LOCKING: * Inherited from caller. */ int ata_sas_port_start(struct ata_port *ap) { return ata_pad_alloc(ap, ap->dev); } EXPORT_SYMBOL_GPL(ata_sas_port_start); /** * ata_port_stop - Undo ata_sas_port_start() * @ap: Port to shut down * * Frees the DMA pad. * * May be used as the port_stop() entry in ata_port_operations. * * LOCKING: * Inherited from caller. */ void ata_sas_port_stop(struct ata_port *ap) { ata_pad_free(ap, ap->dev); } EXPORT_SYMBOL_GPL(ata_sas_port_stop); /** * ata_sas_port_init - Initialize a SATA device * @ap: SATA port to initialize * * LOCKING: * PCI/etc. bus probe sem. * * RETURNS: * Zero on success, non-zero on error. */ int ata_sas_port_init(struct ata_port *ap) { int rc = ap->ops->port_start(ap); if (!rc) { ap->print_id = ata_print_id++; rc = ata_bus_probe(ap); } return rc; } EXPORT_SYMBOL_GPL(ata_sas_port_init); /** * ata_sas_port_destroy - Destroy a SATA port allocated by ata_sas_port_alloc * @ap: SATA port to destroy * */ void ata_sas_port_destroy(struct ata_port *ap) { if (ap->ops->port_stop) ap->ops->port_stop(ap); kfree(ap); } EXPORT_SYMBOL_GPL(ata_sas_port_destroy); /** * ata_sas_slave_configure - Default slave_config routine for libata devices * @sdev: SCSI device to configure * @ap: ATA port to which SCSI device is attached * * RETURNS: * Zero. */ int ata_sas_slave_configure(struct scsi_device *sdev, struct ata_port *ap) { ata_scsi_sdev_config(sdev); ata_scsi_dev_config(sdev, ap->device); return 0; } EXPORT_SYMBOL_GPL(ata_sas_slave_configure); /** * ata_sas_queuecmd - Issue SCSI cdb to libata-managed device * @cmd: SCSI command to be sent * @done: Completion function, called when command is complete * @ap: ATA port to which the command is being sent * * RETURNS: * Return value from __ata_scsi_queuecmd() if @cmd can be queued, * 0 otherwise. */ int ata_sas_queuecmd(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *), struct ata_port *ap) { int rc = 0; ata_scsi_dump_cdb(ap, cmd); if (likely(ata_scsi_dev_enabled(ap->device))) rc = __ata_scsi_queuecmd(cmd, done, ap->device); else { cmd->result = (DID_BAD_TARGET << 16); done(cmd); } return rc; } EXPORT_SYMBOL_GPL(ata_sas_queuecmd);